{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/ucf101","name":"UCF101","full_name":"UCF101 Human Actions dataset","description_markdown":"**UCF101** dataset is an extension of UCF50 and consists of 13,320 video clips, which are classified into 101 categories. These 101 categories can be classified into 5 types (Body motion, Human-human interactions, Human-object interactions, Playing musical instruments and Sports). The total length of these video clips is over 27 hours. All the videos are collected from YouTube and have a fixed frame rate of 25 FPS with the resolution of 320 × 240.\r\n\r\nSource: [Two-stream Collaborative Learning with Spatial-Temporal Attention for Video Classification](https://arxiv.org/abs/1711.03273)\r\nImage Source: [https://www.crcv.ucf.edu/data/UCF101.php](https://www.crcv.ucf.edu/data/UCF101.php)","description_withheld":null,"homepage":"https://www.crcv.ucf.edu/data/UCF101.php","introduced_date":"2012-12-03","introduced_date_note":null,"introduced_by":{"paper":"/paper/ucf101-a-dataset-of-101-human-actions-classes","title":"UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild","first_author":"Khurram Soomro","url":null},"license":{"name":"MIT","url":null},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Zero-Shot Learning","url":"/task/zero-shot-learning","datasets_with_task":"/datasets/task/zero-shot-learning"},{"name":"Action Recognition","url":"/task/action-recognition-in-videos","datasets_with_task":"/datasets/task/action-recognition-in-videos"},{"name":"Temporal Action Localization","url":"/task/action-recognition","datasets_with_task":"/datasets/task/action-recognition"},{"name":"Few-Shot Learning","url":"/task/few-shot-learning","datasets_with_task":"/datasets/task/few-shot-learning"},{"name":"Image Clustering","url":"/task/image-clustering","datasets_with_task":"/datasets/task/image-clustering"},{"name":"Skeleton Based Action Recognition","url":"/task/skeleton-based-action-recognition","datasets_with_task":"/datasets/task/skeleton-based-action-recognition"},{"name":"Action Classification","url":"/task/action-classification","datasets_with_task":"/datasets/task/action-classification"},{"name":"Action Recognition In Videos","url":"/task/action-recognition-in-videos-2","datasets_with_task":"/datasets/task/action-recognition-in-videos-2"},{"name":"Transductive Zero-Shot Classification","url":"/task/transductive-zero-shot-classification","datasets_with_task":"/datasets/task/transductive-zero-shot-classification"},{"name":"Video Frame Interpolation","url":"/task/video-frame-interpolation","datasets_with_task":"/datasets/task/video-frame-interpolation"},{"name":"Video Generation","url":"/task/video-generation","datasets_with_task":"/datasets/task/video-generation"},{"name":"Prompt Engineering","url":"/task/prompt-engineering","datasets_with_task":"/datasets/task/prompt-engineering"},{"name":"Few-Shot Learning - 4 shots","url":"/task/few-shot-learning-4-shots","datasets_with_task":"/datasets/task/few-shot-learning-4-shots"},{"name":"Human Activity Recognition","url":"/task/human-activity-recognition","datasets_with_task":"/datasets/task/human-activity-recognition"},{"name":"Zero-Shot Action Recognition","url":"/task/zero-shot-action-recognition","datasets_with_task":"/datasets/task/zero-shot-action-recognition"},{"name":"Self-Supervised Action Recognition","url":"/task/self-supervised-action-recognition","datasets_with_task":"/datasets/task/self-supervised-action-recognition"},{"name":"Text-to-Video Generation","url":"/task/text-to-video-generation","datasets_with_task":"/datasets/task/text-to-video-generation"},{"name":"Few Shot Action Recognition","url":"/task/few-shot-action-recognition","datasets_with_task":"/datasets/task/few-shot-action-recognition"},{"name":"Early Action Prediction","url":"/task/early-action-prediction","datasets_with_task":"/datasets/task/early-action-prediction"},{"name":"Self-Supervised Action Recognition Linear","url":"/task/self-supervised-action-recognition-linear","datasets_with_task":"/datasets/task/self-supervised-action-recognition-linear"},{"name":"Self-supervised Video Retrieval","url":"/task/self-supervised-video-retrieval","datasets_with_task":"/datasets/task/self-supervised-video-retrieval"},{"name":"Open Set Action Recognition","url":"/task/open-set-action-recognition","datasets_with_task":"/datasets/task/open-set-action-recognition"}],"languages":[{"name":"Korean","url":"/datasets/language/korean"}],"variants":["UCF101-skeleton","UCF101-MiTv2","UCF-101 Zero-shot, 256x256, class-conditional","UCF101 (finetuned)","UCF 101","UCF101","UCF-101 16 frames, Unconditional, Single GPU","UCF-101 16 frames, 64x64, Unconditional","UCF-101 16 frames, 128x128, Unconditional","UCF-101"],"data_loaders":[{"repo":"https://github.com/pytorch/vision","url":"https://pytorch.org/vision/stable/generated/torchvision.datasets.UCF101.html","frameworks":["pytorch"]},{"repo":"https://github.com/voxel51/fiftyone","url":"https://docs.voxel51.com/user_guide/dataset_zoo/datasets.html#ucf101","frameworks":["tf","pytorch"]},{"repo":"https://github.com/open-mmlab/mmaction2","url":"https://github.com/open-mmlab/mmaction2/blob/master/tools/data/ucf101/README.md","frameworks":["pytorch"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/ucf101","frameworks":["tf","jax"]}],"num_papers_in_archive":1863,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/action-recognition-in-videos-on-ucf101","task":"Action Recognition","dataset_variant":"UCF101","rows":91,"metrics":["3-fold Accuracy","Accuracy","Accuracy 20%Test"],"first_row_in_archive_order":{"model":"FTP-UniFormerV2-L/14","paper":"/paper/enhancing-video-transformers-for-action","metrics":{"3-fold Accuracy":"99.7"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/self-supervised-action-recognition-on-ucf101","task":"Self-Supervised Action Recognition","dataset_variant":"UCF101","rows":53,"metrics":["3-fold Accuracy","Pre-Training Dataset","Frozen","split-1  Top-1 Accuracy"],"first_row_in_archive_order":{"model":"VideoMAE V2-g","paper":"/paper/videomae-v2-scaling-video-masked-autoencoders","metrics":{"3-fold Accuracy":"99.6"},"code_links":[{"title":"OpenGVLab/VideoMAEv2","url":"https://github.com/OpenGVLab/VideoMAEv2"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-generation-on-ucf-101","task":"Video Generation","dataset_variant":"UCF-101","rows":48,"metrics":["FVD16","FVD128","Inception Score","KVD16"],"first_row_in_archive_order":{"model":"W.A.L.T-XL (class-conditional)","paper":"/paper/photorealistic-video-generation-with","metrics":{"FVD16":"36±2"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/zero-shot-action-recognition-on-ucf101","task":"Zero-Shot Action Recognition","dataset_variant":"UCF101","rows":35,"metrics":["Top-1 Accuracy","Top-5 accuracy"],"first_row_in_archive_order":{"model":"OTI(ViT-L/14)","paper":"/paper/orthogonal-temporal-interpolation-for-zero","metrics":{"Top-1 Accuracy":"92.8"},"code_links":[{"title":"sweetorangezhuyan/mm2023_oti","url":"https://github.com/sweetorangezhuyan/mm2023_oti"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-frame-interpolation-on-ucf101-1","task":"Video Frame Interpolation","dataset_variant":"UCF101","rows":19,"metrics":["PSNR","SSIM","PSNR (sRGB)","LPIPS"],"first_row_in_archive_order":{"model":"EMA-VFI","paper":"/paper/extracting-motion-and-appearance-via-inter","metrics":{"PSNR":"35.48","SSIM":"0.9701"},"code_links":[{"title":"mcg-nju/ema-vfi","url":"https://github.com/mcg-nju/ema-vfi"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/prompt-engineering-on-ucf101","task":"Prompt Engineering","dataset_variant":"UCF101","rows":14,"metrics":["Harmonic mean"],"first_row_in_archive_order":{"model":"PromptKD","paper":"/paper/promptkd-unsupervised-prompt-distillation-for","metrics":{"Harmonic mean":"86.10"},"code_links":[{"title":"zhengli97/promptkd","url":"https://github.com/zhengli97/promptkd"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/self-supervised-action-recognition-on-ucf101-1","task":"Self-Supervised Action Recognition","dataset_variant":"UCF101 (finetuned)","rows":14,"metrics":["3-fold Accuracy","Pretrain"],"first_row_in_archive_order":{"model":"BraVe:V-FA (TSM-50x2)","paper":"/paper/broaden-your-views-for-self-supervised-video","metrics":{"3-fold Accuracy":"95.7"},"code_links":[{"title":"deepmind/brave","url":"https://github.com/deepmind/brave"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-to-video-generation-on-ucf-101","task":"Text-to-Video Generation","dataset_variant":"UCF-101","rows":10,"metrics":["FVD16"],"first_row_in_archive_order":{"model":"Snap Video (Zero-shot, 512x288)","paper":"/paper/snap-video-scaled-spatiotemporal-transformers","metrics":{"FVD16":"200.2"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/few-shot-action-recognition-on-ucf101","task":"Few Shot Action Recognition","dataset_variant":"UCF101","rows":7,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"STRM","paper":"/paper/spatio-temporal-relation-modeling-for-few","metrics":{"1:1 Accuracy":"96.8"},"code_links":[{"title":"Anirudh257/strm","url":"https://github.com/Anirudh257/strm"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-generation-on-ucf-101-16-frames","task":"Video Generation","dataset_variant":"UCF-101 16 frames, Unconditional, Single GPU","rows":7,"metrics":["Inception Score"],"first_row_in_archive_order":{"model":"TGAN-F","paper":"/paper/lower-dimensional-kernels-for-video","metrics":{"Inception Score":"22.91"},"code_links":[{"title":"HappyBahman/ldvdGAN","url":"https://github.com/HappyBahman/ldvdGAN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-generation-on-ucf-101-16-frames-64x64","task":"Video Generation","dataset_variant":"UCF-101 16 frames, 64x64, Unconditional","rows":7,"metrics":["Inception Score","FID","FVD"],"first_row_in_archive_order":{"model":"Video Diffusion Model","paper":"/paper/video-diffusion-models","metrics":{"FID":"295","Inception Score":"57"},"code_links":[{"title":"lucidrains/make-a-video-pytorch","url":"https://github.com/lucidrains/make-a-video-pytorch"},{"title":"lucidrains/video-diffusion-pytorch","url":"https://github.com/lucidrains/video-diffusion-pytorch"},{"title":"coderpiaobozhe/classifier-free-diffusion-guidance-Pytorch","url":"https://github.com/coderpiaobozhe/classifier-free-diffusion-guidance-Pytorch"},{"title":"ndrwmlnk/awesome-video-diffusion-models","url":"https://github.com/ndrwmlnk/awesome-video-diffusion-models"},{"title":"eyeline-research/survey-video-diffusion","url":"https://github.com/eyeline-research/survey-video-diffusion"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-generation-on-ucf-101-16-frames-128x128","task":"Video Generation","dataset_variant":"UCF-101 16 frames, 128x128, Unconditional","rows":6,"metrics":["Inception Score"],"first_row_in_archive_order":{"model":"TGANv2 (2020)","paper":"/paper/tganv2-efficient-training-of-large-models-for","metrics":{"Inception Score":"28.87"},"code_links":[{"title":"pfnet-research/tgan2","url":"https://github.com/pfnet-research/tgan2"},{"title":"Zasder3/Tganv2-PyTorch-Train-Sparsely--Generate-Densely","url":"https://github.com/Zasder3/Tganv2-PyTorch-Train-Sparsely--Generate-Densely"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/action-recognition-in-videos-on-ucf101-2","task":"Action Recognition In Videos","dataset_variant":"UCF101","rows":5,"metrics":["3-fold Accuracy"],"first_row_in_archive_order":{"model":"STM (ImageNet+Kinetics pretrain)","paper":"/paper/stm-spatiotemporal-and-motion-encoding-for","metrics":{"3-fold Accuracy":"96.2"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/action-recognition-in-videos-on-ucf-101","task":"Action Recognition","dataset_variant":"UCF-101","rows":2,"metrics":["3-fold Accuracy","Accuracy"],"first_row_in_archive_order":{"model":"DMC-Net (ResNet-18)","paper":"/paper/dmc-net-generating-discriminative-motion-cues","metrics":{"3-fold Accuracy":"90.9"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-clustering-on-ucf101","task":"Image Clustering","dataset_variant":"UCF101","rows":2,"metrics":["Accuracy","ARI","NMI"],"first_row_in_archive_order":{"model":"TURTLE (CLIP + DINOv2)","paper":"/paper/let-go-of-your-labels-with-unsupervised-1","metrics":{"Accuracy":"82.3"},"code_links":[{"title":"mlbio-epfl/turtle","url":"https://github.com/mlbio-epfl/turtle"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/zero-shot-learning-on-ucf101","task":"Zero-Shot Learning","dataset_variant":"UCF101","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ZLaP","paper":"/paper/label-propagation-for-zero-shot","metrics":{"Accuracy":"76.3"},"code_links":[{"title":"vladan-stojnic/zlap","url":"https://github.com/vladan-stojnic/zlap"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/action-classification-on-ucf101","task":"Action Classification","dataset_variant":"UCF101","rows":1,"metrics":["Top-1"],"first_row_in_archive_order":{"model":"Ours","paper":"/paper/spact-self-supervised-privacy-preservation","metrics":{"Top-1":"62.03"},"code_links":[{"title":"daveishan/spact","url":"https://github.com/daveishan/spact"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/action-recognition-on-ucf-101","task":"Action Recognition","dataset_variant":"UCF 101","rows":1,"metrics":["3-fold Accuracy"],"first_row_in_archive_order":{"model":"R2+1D-BERT","paper":"/paper/late-temporal-modeling-in-3d-cnn","metrics":{"3-fold Accuracy":"98.69"},"code_links":[{"title":"artest08/LateTemporalModeling3DCNN","url":"https://github.com/artest08/LateTemporalModeling3DCNN"},{"title":"kietngt00/hmdb51-recognition","url":"https://github.com/kietngt00/hmdb51-recognition"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/few-shot-learning-on-ucf101","task":"Few-Shot Learning","dataset_variant":"UCF101","rows":1,"metrics":["Harmonic mean"],"first_row_in_archive_order":{"model":"Variational Prompt Tuning","paper":"/paper/variational-prompt-tuning-improves","metrics":{"Harmonic mean":"79"},"code_links":[{"title":"saic-fi/bayesian-prompt-learning","url":"https://github.com/saic-fi/bayesian-prompt-learning"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/human-activity-recognition-on-ucf-101","task":"Human Activity Recognition","dataset_variant":"UCF 101","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Label-Ranker","paper":"/paper/label-ranker-self-aware-preference-for","metrics":{"Accuracy":"89.50%"},"code_links":[{"title":"Peihao-Xiang/Label-Ranker","url":"https://github.com/Peihao-Xiang/Label-Ranker"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/open-set-action-recognition-on-ucf101-mitv2","task":"Open Set Action Recognition","dataset_variant":"UCF101-MiTv2","rows":1,"metrics":["AUROC"],"first_row_in_archive_order":{"model":"InternVideo","paper":"/paper/internvideo-general-video-foundation-models","metrics":{"AUROC":"91.85"},"code_links":[{"title":"opengvlab/internvideo","url":"https://github.com/opengvlab/internvideo"},{"title":"yingsen1/unimd","url":"https://github.com/yingsen1/unimd"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/skeleton-based-action-recognition-on-ucf101","task":"Skeleton Based Action Recognition","dataset_variant":"UCF101","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Structured Keypoint Pooling","paper":"/paper/unified-keypoint-based-action-recognition","metrics":{"Accuracy":"87.8"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/transductive-zero-shot-classification-on-9","task":"Transductive Zero-Shot Classification","dataset_variant":"UCF101","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ZLaP","paper":"/paper/label-propagation-for-zero-shot","metrics":{"Accuracy":"77.7"},"code_links":[{"title":"vladan-stojnic/zlap","url":"https://github.com/vladan-stojnic/zlap"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":3,"rows_per_page":100,"shown":100,"of":228,"counts":{"papers_with_a_benchmark_row":228,"with_a_code_link":162,"where_syntology_ran_a_sample":75,"not_listed_spam_title":0,"listed":228,"listed_where_code_ran":75,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":65,"every_run_a_failure_of_syntologys_instrument":10,"listed_with_a_run_with_no_instrument_failure":65,"listed_every_run_a_failure_of_syntologys_instrument":10,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/video-gpt-via-next-clip-diffusion","slug":"video-gpt-via-next-clip-diffusion","title":"Video-GPT via Next Clip Diffusion","date":"2025-05-18","arxiv_id":"2505.12489","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mmrl-parameter-efficient-and-interaction","slug":"mmrl-parameter-efficient-and-interaction","title":"MMRL++: Parameter-Efficient and Interaction-Aware Representation Learning for Vision-Language Models","date":"2025-05-15","arxiv_id":"2505.10088","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/ca-2st-cross-attention-in-audio-space-and","slug":"ca-2st-cross-attention-in-audio-space-and","title":"CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition","date":"2025-03-30","arxiv_id":"2503.23447","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/long-context-autoregressive-video-modeling-1","slug":"long-context-autoregressive-video-modeling-1","title":"Long-Context Autoregressive Video Modeling with Next-Frame Prediction","date":"2025-03-25","arxiv_id":"2503.19325","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/leanvae-an-ultra-efficient-reconstruction-vae","slug":"leanvae-an-ultra-efficient-reconstruction-vae","title":"LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion Models","date":"2025-03-18","arxiv_id":"2503.14325","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["westlake-repl/leanvae"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/leanvae-an-ultra-efficient-reconstruction-vae#ran","syntology_url":"https://syntology.ai/paper/2503.14325","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.14325"}}}},{"paper":"/paper/mmrl-multi-modal-representation-learning-for","slug":"mmrl-multi-modal-representation-learning-for","title":"MMRL: Multi-Modal Representation Learning for Vision-Language Models","date":"2025-03-11","arxiv_id":"2503.08497","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["yunncheng/MMRL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mmrl-multi-modal-representation-learning-for#ran","syntology_url":"https://syntology.ai/paper/2503.08497","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.08497"}}}},{"paper":"/paper/label-ranker-self-aware-preference-for","slug":"label-ranker-self-aware-preference-for","title":"Label Ranker: Self-Aware Preference for Classification Label Position in Visual Masked Self-Supervised Pre-Trained Model","date":"2025-03-03","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/acdit-interpolating-autoregressive","slug":"acdit-interpolating-autoregressive","title":"ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer","date":"2024-12-10","arxiv_id":"2412.07720","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["thunlp/acdit"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/acdit-interpolating-autoregressive#ran","syntology_url":"https://syntology.ai/paper/2412.07720","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07720"}}}},{"paper":"/paper/locate-gat-modeling-multi-scale-local-context","slug":"locate-gat-modeling-multi-scale-local-context","title":"LoCATe-GAT: Modeling Multi-Scale Local Context and Action Relationships for Zero-Shot Action Recognition","date":"2024-11-27","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/larp-tokenizing-videos-with-a-learned-1","slug":"larp-tokenizing-videos-with-a-learned-1","title":"LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior","date":"2024-10-28","arxiv_id":"2410.21264","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/larp-tokenizing-videos-with-a-learned-1#ran","syntology_url":"https://syntology.ai/paper/2410.21264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21264"}}}},{"paper":"/paper/hpt-hierarchically-prompting-vision-language","slug":"hpt-hierarchically-prompting-vision-language","title":"HPT++: Hierarchically Prompting Vision-Language Models with Multi-Granularity Knowledge Generation and Improved Structure Modeling","date":"2024-08-27","arxiv_id":"2408.14812","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/vfimamba-video-frame-interpolation-with-state","slug":"vfimamba-video-frame-interpolation-with-state","title":"VFIMamba: Video Frame Interpolation with State Space Models","date":"2024-07-02","arxiv_id":"2407.02315","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":5,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["mcg-nju/vfimamba"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vfimamba-video-frame-interpolation-with-state#ran","syntology_url":"https://syntology.ai/paper/2407.02315","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02315"}}}},{"paper":"/paper/omnitokenizer-a-joint-image-video-tokenizer","slug":"omnitokenizer-a-joint-image-video-tokenizer","title":"OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation","date":"2024-06-13","arxiv_id":"2406.09399","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["foundationvision/omnitokenizer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/omnitokenizer-a-joint-image-video-tokenizer#ran","syntology_url":"https://syntology.ai/paper/2406.09399","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09399"}}}},{"paper":"/paper/hierarchical-patch-diffusion-models-for-high-1","slug":"hierarchical-patch-diffusion-models-for-high-1","title":"Hierarchical Patch Diffusion Models for High-Resolution Video Generation","date":"2024-06-12","arxiv_id":"2406.07792","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/let-go-of-your-labels-with-unsupervised-1","slug":"let-go-of-your-labels-with-unsupervised-1","title":"Let Go of Your Labels with Unsupervised Transfer","date":"2024-06-11","arxiv_id":"2406.07236","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":4,"official":{"repos":["mlbio-epfl/turtle"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/let-go-of-your-labels-with-unsupervised-1#ran","syntology_url":"https://syntology.ai/paper/2406.07236","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07236"}}}},{"paper":"/paper/fifo-diffusion-generating-infinite-videos","slug":"fifo-diffusion-generating-infinite-videos","title":"FIFO-Diffusion: Generating Infinite Videos from Text without Training","date":"2024-05-19","arxiv_id":"2405.11473","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":5,"samples_unverified":3,"pointer_only_for_licence":13,"official":{"repos":["jjihwan/FIFO-Diffusion_public"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/fifo-diffusion-generating-infinite-videos#ran","syntology_url":"https://syntology.ai/paper/2405.11473","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.11473"}}}},{"paper":"/paper/leveraging-temporal-contextualization-for","slug":"leveraging-temporal-contextualization-for","title":"Leveraging Temporal Contextualization for Video Action Recognition","date":"2024-04-15","arxiv_id":"2404.09490","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":4,"official":{"repos":["naver-ai/tc-clip"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/leveraging-temporal-contextualization-for#ran","syntology_url":"https://syntology.ai/paper/2404.09490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09490"}}}},{"paper":"/paper/label-propagation-for-zero-shot","slug":"label-propagation-for-zero-shot","title":"Label Propagation for Zero-shot Classification with Vision-Language Models","date":"2024-04-05","arxiv_id":"2404.04072","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["vladan-stojnic/zlap"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/label-propagation-for-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2404.04072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04072"}}}},{"paper":"/paper/prompt-learning-via-meta-regularization","slug":"prompt-learning-via-meta-regularization","title":"Prompt Learning via Meta-Regularization","date":"2024-04-01","arxiv_id":"2404.00851","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":2,"official":{"repos":["mlvlab/prometar"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/prompt-learning-via-meta-regularization#ran","syntology_url":"https://syntology.ai/paper/2404.00851","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00851"}}}},{"paper":"/paper/grid-diffusion-models-for-text-to-video-1","slug":"grid-diffusion-models-for-text-to-video-1","title":"Grid Diffusion Models for Text-to-Video Generation","date":"2024-03-30","arxiv_id":"2404.00234","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/enhancing-video-transformers-for-action","slug":"enhancing-video-transformers-for-action","title":"Enhancing Video Transformers for Action Understanding with VLM-aided Training","date":"2024-03-24","arxiv_id":"2403.16128","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/promptkd-unsupervised-prompt-distillation-for","slug":"promptkd-unsupervised-prompt-distillation-for","title":"PromptKD: Unsupervised Prompt Distillation for Vision-Language Models","date":"2024-03-05","arxiv_id":"2403.02781","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/snap-video-scaled-spatiotemporal-transformers","slug":"snap-video-scaled-spatiotemporal-transformers","title":"Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis","date":"2024-02-22","arxiv_id":"2402.14797","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/video-lavit-unified-video-language-pre","slug":"video-lavit-unified-video-language-pre","title":"Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization","date":"2024-02-05","arxiv_id":"2402.03161","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":5,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-lavit-unified-video-language-pre#ran","syntology_url":"https://syntology.ai/paper/2402.03161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03161"}}}},{"paper":"/paper/lumiere-a-space-time-diffusion-model-for","slug":"lumiere-a-space-time-diffusion-model-for","title":"Lumiere: A Space-Time Diffusion Model for Video Generation","date":"2024-01-23","arxiv_id":"2401.12945","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/lumiere-a-space-time-diffusion-model-for#ran","syntology_url":"https://syntology.ai/paper/2401.12945","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.12945"}}}},{"paper":"/paper/omnivec2-a-novel-transformer-based-network","slug":"omnivec2-a-novel-transformer-based-network","title":"OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","date":"2024-01-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/videopoet-a-large-language-model-for-zero","slug":"videopoet-a-large-language-model-for-zero","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","date":"2023-12-21","arxiv_id":"2312.14125","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/ez-clip-efficient-zeroshot-video-action","slug":"ez-clip-efficient-zeroshot-video-action","title":"EZ-CLIP: Efficient Zeroshot Video Action Recognition","date":"2023-12-13","arxiv_id":"2312.08010","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":9,"samples_unverified":4,"pointer_only_for_licence":4,"official":{"repos":["shahzadnit/ez-clip"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ez-clip-efficient-zeroshot-video-action#ran","syntology_url":"https://syntology.ai/paper/2312.08010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.08010"}}}},{"paper":"/paper/learning-hierarchical-prompt-with-structured","slug":"learning-hierarchical-prompt-with-structured","title":"Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models","date":"2023-12-11","arxiv_id":"2312.06323","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":5,"official":{"repos":["vill-lab/2024-aaai-hpt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-hierarchical-prompt-with-structured#ran","syntology_url":"https://syntology.ai/paper/2312.06323","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06323"}}}},{"paper":"/paper/photorealistic-video-generation-with","slug":"photorealistic-video-generation-with","title":"Photorealistic Video Generation with Diffusion Models","date":"2023-12-11","arxiv_id":"2312.06662","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/ost-refining-text-knowledge-with-optimal","slug":"ost-refining-text-knowledge-with-optimal","title":"OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition","date":"2023-11-30","arxiv_id":"2312.00096","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["tomchen-ctj/OST"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ost-refining-text-knowledge-with-optimal#ran","syntology_url":"https://syntology.ai/paper/2312.00096","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00096"}}}},{"paper":"/paper/videoassembler-identity-consistent-video","slug":"videoassembler-identity-consistent-video","title":"MagDiff: Multi-Alignment Diffusion for High-Fidelity Video Generation and Editing","date":"2023-11-29","arxiv_id":"2311.17338","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":12,"official":{"repos":["gulucaptain/videoassembler"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/videoassembler-identity-consistent-video#ran","syntology_url":"https://syntology.ai/paper/2311.17338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17338"}}}},{"paper":"/paper/make-pixels-dance-high-dynamic-video","slug":"make-pixels-dance-high-dynamic-video","title":"Make Pixels Dance: High-Dynamic Video Generation","date":"2023-11-18","arxiv_id":"2311.10982","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/omnivec-learning-robust-representations-with","slug":"omnivec-learning-robust-representations-with","title":"OmniVec: Learning robust representations with cross modal sharing","date":"2023-11-07","arxiv_id":"2311.05709","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/asymmetric-masked-distillation-for-pre","slug":"asymmetric-masked-distillation-for-pre","title":"Asymmetric Masked Distillation for Pre-Training Small Foundation Models","date":"2023-11-06","arxiv_id":"2311.03149","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/regis-refining-generated-videos-via-iterative","slug":"regis-refining-generated-videos-via-iterative","title":"REGIS: Refining Generated Videos via Iterative Stylistic Redesigning","date":"2023-11-03","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/image-clustering-with-external-guidance","slug":"image-clustering-with-external-guidance","title":"Image Clustering with External Guidance","date":"2023-10-18","arxiv_id":"2310.11989","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":9,"official":{"repos":["xlearning-scu/2024-icml-tac"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/image-clustering-with-external-guidance#ran","syntology_url":"https://syntology.ai/paper/2310.11989","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.11989"}}}},{"paper":"/paper/language-model-beats-diffusion-tokenizer-is","slug":"language-model-beats-diffusion-tokenizer-is","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","date":"2023-10-09","arxiv_id":"2310.05737","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":20,"samples_ran":19,"samples_constructed":0,"samples_ran_checked":14,"samples_ran_instrument_failed":5,"samples_unverified":1,"pointer_only_for_licence":5,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/language-model-beats-diffusion-tokenizer-is#ran","syntology_url":"https://syntology.ai/paper/2310.05737","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05737"}}}},{"paper":"/paper/zeroi2v-zero-cost-adaptation-of-pre-trained","slug":"zeroi2v-zero-cost-adaptation-of-pre-trained","title":"ZeroI2V: Zero-Cost Adaptation of Pre-trained Transformers from Image to Video","date":"2023-10-02","arxiv_id":"2310.01324","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["mcg-nju/zeroi2v","leexinhao/ZeroI2V"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/zeroi2v-zero-cost-adaptation-of-pre-trained#ran","syntology_url":"https://syntology.ai/paper/2310.01324","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01324"}}}},{"paper":"/paper/lavie-high-quality-video-generation-with","slug":"lavie-high-quality-video-generation-with","title":"LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models","date":"2023-09-26","arxiv_id":"2309.15103","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["Vchitect/LaVie"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/lavie-high-quality-video-generation-with#ran","syntology_url":"https://syntology.ai/paper/2309.15103","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.15103"}}}},{"paper":"/paper/dept-decoupled-prompt-tuning","slug":"dept-decoupled-prompt-tuning","title":"DePT: Decoupled Prompt Tuning","date":"2023-09-14","arxiv_id":"2309.07439","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":4,"pointer_only_for_licence":8,"official":{"repos":["koorye/dept"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/dept-decoupled-prompt-tuning#ran","syntology_url":"https://syntology.ai/paper/2309.07439","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07439"}}}},{"paper":"/paper/read-only-prompt-optimization-for-vision","slug":"read-only-prompt-optimization-for-vision","title":"Read-only Prompt Optimization for Vision-Language Few-shot Learning","date":"2023-08-29","arxiv_id":"2308.14960","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["mlvlab/rpo"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/read-only-prompt-optimization-for-vision#ran","syntology_url":"https://syntology.ai/paper/2308.14960","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.14960"}}}},{"paper":"/paper/orthogonal-temporal-interpolation-for-zero","slug":"orthogonal-temporal-interpolation-for-zero","title":"Orthogonal Temporal Interpolation for Zero-Shot Video Recognition","date":"2023-08-14","arxiv_id":"2308.06897","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["sweetorangezhuyan/mm2023_oti"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/orthogonal-temporal-interpolation-for-zero#ran","syntology_url":"https://syntology.ai/paper/2308.06897","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06897"}}}},{"paper":"/paper/self-regulating-prompts-foundational-model","slug":"self-regulating-prompts-foundational-model","title":"Self-regulating Prompts: Foundational Model Adaptation without Forgetting","date":"2023-07-13","arxiv_id":"2307.06948","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":17,"samples_constructed":0,"samples_ran_checked":12,"samples_ran_instrument_failed":5,"samples_unverified":4,"pointer_only_for_licence":3,"official":{"repos":["muzairkhattak/promptsrc"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/self-regulating-prompts-foundational-model#ran","syntology_url":"https://syntology.ai/paper/2307.06948","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.06948"}}}},{"paper":"/paper/benchmarking-self-supervised-video","slug":"benchmarking-self-supervised-video","title":"A Large-Scale Analysis on Self-Supervised Video Representation Learning","date":"2023-06-09","arxiv_id":"2306.06010","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/consistency-guided-prompt-learning-for-vision","slug":"consistency-guided-prompt-learning-for-vision","title":"Consistency-guided Prompt Learning for Vision-Language Models","date":"2023-06-01","arxiv_id":"2306.01195","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":4,"official":{"repos":["shuvenduroy/coprompt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/consistency-guided-prompt-learning-for-vision#ran","syntology_url":"https://syntology.ai/paper/2306.01195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.01195"}}}},{"paper":"/paper/preserve-your-own-correlation-a-noise-prior","slug":"preserve-your-own-correlation-a-noise-prior","title":"Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models","date":"2023-05-17","arxiv_id":"2305.10474","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/alternating-gradient-descent-and-mixture-of","slug":"alternating-gradient-descent-and-mixture-of","title":"Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception","date":"2023-05-10","arxiv_id":"2305.06324","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/video-frame-interpolation-with-densely","slug":"video-frame-interpolation-with-densely","title":"Video Frame Interpolation with Densely Queried Bilateral Correlation","date":"2023-04-26","arxiv_id":"2304.13596","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["kinoud/DQBC"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-frame-interpolation-with-densely#ran","syntology_url":"https://syntology.ai/paper/2304.13596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.13596"}}}},{"paper":"/paper/align-your-latents-high-resolution-video","slug":"align-your-latents-high-resolution-video","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","date":"2023-04-18","arxiv_id":"2304.08818","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":26,"samples_ran":18,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":9,"samples_unverified":8,"pointer_only_for_licence":3,"official":{"repos":["stability-ai/generative-models"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/align-your-latents-high-resolution-video#ran","syntology_url":"https://syntology.ai/paper/2304.08818","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.08818"}}}},{"paper":"/paper/synthetic-sample-selection-for-generalized","slug":"synthetic-sample-selection-for-generalized","title":"Synthetic Sample Selection for Generalized Zero-Shot Learning","date":"2023-04-06","arxiv_id":"2304.02846","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/victr-video-conditioned-text-representations","slug":"victr-video-conditioned-text-representations","title":"VicTR: Video-conditioned Text Representations for Activity Recognition","date":"2023-04-05","arxiv_id":"2304.02560","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/videomae-v2-scaling-video-masked-autoencoders","slug":"videomae-v2-scaling-video-masked-autoencoders","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","date":"2023-03-29","arxiv_id":"2303.16727","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["OpenGVLab/VideoMAEv2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/videomae-v2-scaling-video-masked-autoencoders#ran","syntology_url":"https://syntology.ai/paper/2303.16727","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16727"}}}},{"paper":"/paper/eva-clip-improved-training-techniques-for","slug":"eva-clip-improved-training-techniques-for","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","date":"2023-03-27","arxiv_id":"2303.15389","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["baaivision/eva"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/eva-clip-improved-training-techniques-for#ran","syntology_url":"https://syntology.ai/paper/2303.15389","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.15389"}}}},{"paper":"/paper/unified-keypoint-based-action-recognition","slug":"unified-keypoint-based-action-recognition","title":"Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling","date":"2023-03-27","arxiv_id":"2303.15270","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/towards-end-to-end-generative-modeling-of","slug":"towards-end-to-end-generative-modeling-of","title":"Towards End-to-End Generative Modeling of Long Videos with Memory-Efficient Bidirectional Transformers","date":"2023-03-20","arxiv_id":"2303.11251","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/decomposed-diffusion-models-for-high-quality","slug":"decomposed-diffusion-models-for-high-quality","title":"VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation","date":"2023-03-15","arxiv_id":"2303.08320","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/match-expand-and-improve-unsupervised","slug":"match-expand-and-improve-unsupervised","title":"MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge","date":"2023-03-15","arxiv_id":"2303.08914","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":4,"official":{"repos":["wlin-at/maxi"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/match-expand-and-improve-unsupervised#ran","syntology_url":"https://syntology.ai/paper/2303.08914","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08914"}}}},{"paper":"/paper/extracting-motion-and-appearance-via-inter","slug":"extracting-motion-and-appearance-via-inter","title":"Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation","date":"2023-03-01","arxiv_id":"2303.00440","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":10,"samples_constructed":5,"samples_ran_checked":6,"samples_ran_instrument_failed":4,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["mcg-nju/ema-vfi"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/extracting-motion-and-appearance-via-inter#ran","syntology_url":"https://syntology.ai/paper/2303.00440","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.00440"}}}},{"paper":"/paper/video-action-recognition-collaborative","slug":"video-action-recognition-collaborative","title":"Video Action Recognition Collaborative Learning with Dynamics via PSO-ConvNet Transformer","date":"2023-02-17","arxiv_id":"2302.09187","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/bidirectional-cross-modal-knowledge","slug":"bidirectional-cross-modal-knowledge","title":"Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models","date":"2022-12-31","arxiv_id":"2301.00182","rows_on_this_dataset":2,"code_links":5,"syntology":null},{"paper":"/paper/adaptive-frame-selection-in-two-dimensional","slug":"adaptive-frame-selection-in-two-dimensional","title":"Adaptive frame selection in two dimensional convolutional neural network action recognition","date":"2022-12-28","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/similarity-contrastive-estimation-for-image","slug":"similarity-contrastive-estimation-for-image","title":"Similarity Contrastive Estimation for Image and Video Soft Contrastive Self-Supervised Learning","date":"2022-12-21","arxiv_id":"2212.11187","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/magvit-masked-generative-video-transformer","slug":"magvit-masked-generative-video-transformer","title":"MAGVIT: Masked Generative Video Transformer","date":"2022-12-10","arxiv_id":"2212.05199","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["google-research/magvit"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/magvit-masked-generative-video-transformer#ran","syntology_url":"https://syntology.ai/paper/2212.05199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.05199"}}}},{"paper":"/paper/video-text-modeling-with-zero-shot-transfer","slug":"video-text-modeling-with-zero-shot-transfer","title":"VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners","date":"2022-12-09","arxiv_id":"2212.04979","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-domain-invariant-prompt-for-vision","slug":"learning-domain-invariant-prompt-for-vision","title":"Learning Domain Invariant Prompt for Vision-Language Models","date":"2022-12-08","arxiv_id":"2212.04196","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/masked-video-distillation-rethinking-masked","slug":"masked-video-distillation-rethinking-masked","title":"Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning","date":"2022-12-08","arxiv_id":"2212.04500","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/internvideo-general-video-foundation-models","slug":"internvideo-general-video-foundation-models","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","date":"2022-12-06","arxiv_id":"2212.03191","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["opengvlab/internvideo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/internvideo-general-video-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2212.03191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03191"}}}},{"paper":"/paper/vidm-video-implicit-diffusion-models","slug":"vidm-video-implicit-diffusion-models","title":"VIDM: Video Implicit Diffusion Models","date":"2022-12-01","arxiv_id":"2212.00235","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["MKFMIKU/VIDM"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vidm-video-implicit-diffusion-models#ran","syntology_url":"https://syntology.ai/paper/2212.00235","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.00235"}}}},{"paper":"/paper/xkd-cross-modal-knowledge-distillation-with","slug":"xkd-cross-modal-knowledge-distillation-with","title":"XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning","date":"2022-11-25","arxiv_id":"2211.13929","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/latent-video-diffusion-models-for-high","slug":"latent-video-diffusion-models-for-high","title":"Latent Video Diffusion Models for High-Fidelity Long Video Generation","date":"2022-11-23","arxiv_id":"2211.13221","rows_on_this_dataset":5,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":13,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":7,"samples_unverified":1,"pointer_only_for_licence":5,"official":{"repos":["yingqinghe/lvdm"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/latent-video-diffusion-models-for-high#ran","syntology_url":"https://syntology.ai/paper/2211.13221","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.13221"}}}},{"paper":"/paper/tell-me-what-happened-unifying-text-guided","slug":"tell-me-what-happened-unifying-text-guided","title":"Tell Me What Happened: Unifying Text-guided Video Completion via Multimodal Masked Video Generation","date":"2022-11-23","arxiv_id":"2211.12824","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/magicvideo-efficient-video-generation-with","slug":"magicvideo-efficient-video-generation-with","title":"MagicVideo: Efficient Video Generation With Latent Diffusion Models","date":"2022-11-20","arxiv_id":"2211.11018","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/efficient-video-representation-learning-via","slug":"efficient-video-representation-learning-via","title":"EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens","date":"2022-11-19","arxiv_id":"2211.10636","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":3,"samples_constructed":3,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":6,"official":{"repos":["sunilhoho/everest","sunilhoho/VideoMS"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/efficient-video-representation-learning-via#ran","syntology_url":"https://syntology.ai/paper/2211.10636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.10636"}}}},{"paper":"/paper/a-unified-pyramid-recurrent-network-for-video","slug":"a-unified-pyramid-recurrent-network-for-video","title":"A Unified Pyramid Recurrent Network for Video Frame Interpolation","date":"2022-11-07","arxiv_id":"2211.03456","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/m-3-video-masked-motion-modeling-for-self","slug":"m-3-video-masked-motion-modeling-for-self","title":"Masked Motion Encoding for Self-Supervised Video Representation Learning","date":"2022-10-12","arxiv_id":"2210.06096","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/maple-multi-modal-prompt-learning","slug":"maple-multi-modal-prompt-learning","title":"MaPLe: Multi-modal Prompt Learning","date":"2022-10-06","arxiv_id":"2210.03117","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["muzairkhattak/multimodal-prompt-learning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/maple-multi-modal-prompt-learning#ran","syntology_url":"https://syntology.ai/paper/2210.03117","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03117"}}}},{"paper":"/paper/variational-prompt-tuning-improves","slug":"variational-prompt-tuning-improves","title":"Bayesian Prompt Learning for Image-Language Model Generalization","date":"2022-10-05","arxiv_id":"2210.02390","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":3,"official":{"repos":["saic-fi/bayesian-prompt-learning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/variational-prompt-tuning-improves#ran","syntology_url":"https://syntology.ai/paper/2210.02390","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.02390"}}}},{"paper":"/paper/make-a-video-text-to-video-generation-without","slug":"make-a-video-text-to-video-generation-without","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","date":"2022-09-29","arxiv_id":"2209.14792","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/expanding-language-image-pretrained-models","slug":"expanding-language-image-pretrained-models","title":"Expanding Language-Image Pretrained Models for General Video Recognition","date":"2022-08-04","arxiv_id":"2208.02816","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":3,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["microsoft/videox"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/expanding-language-image-pretrained-models#ran","syntology_url":"https://syntology.ai/paper/2208.02816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.02816"}}}},{"paper":"/paper/multimodal-open-vocabulary-video","slug":"multimodal-open-vocabulary-video","title":"Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models","date":"2022-07-15","arxiv_id":"2207.07646","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/neighbor-correspondence-matching-for-flow","slug":"neighbor-correspondence-matching-for-flow","title":"Neighbor Correspondence Matching for Flow-based Video Frame Synthesis","date":"2022-07-14","arxiv_id":"2207.06763","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/federated-self-supervised-learning-for-video","slug":"federated-self-supervised-learning-for-video","title":"Federated Self-supervised Learning for Video Understanding","date":"2022-07-05","arxiv_id":"2207.01975","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/transferring-textual-knowledge-for-visual","slug":"transferring-textual-knowledge-for-visual","title":"Revisiting Classifier: Transferring Vision-Language Models for Video Recognition","date":"2022-07-04","arxiv_id":"2207.01297","rows_on_this_dataset":2,"code_links":5,"syntology":null},{"paper":"/paper/slic-self-supervised-learning-with-iterative-1","slug":"slic-self-supervised-learning-with-iterative-1","title":"SLIC: Self-Supervised Learning with Iterative Clustering for Human Action Videos","date":"2022-06-25","arxiv_id":"2206.12534","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/enhanced-bi-directional-motion-estimation-for","slug":"enhanced-bi-directional-motion-estimation-for","title":"Enhanced Bi-directional Motion Estimation for Video Frame Interpolation","date":"2022-06-17","arxiv_id":"2206.08572","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learn2augment-learning-to-composite-videos","slug":"learn2augment-learning-to-composite-videos","title":"Learn2Augment: Learning to Composite Videos for Data Augmentation in Action Recognition","date":"2022-06-09","arxiv_id":"2206.04790","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/cogvideo-large-scale-pretraining-for-text-to","slug":"cogvideo-large-scale-pretraining-for-text-to","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","date":"2022-05-29","arxiv_id":"2205.15868","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/ifrnet-intermediate-feature-refine-network","slug":"ifrnet-intermediate-feature-refine-network","title":"IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation","date":"2022-05-29","arxiv_id":"2205.14620","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":20,"samples_ran":17,"samples_constructed":2,"samples_ran_checked":13,"samples_ran_instrument_failed":4,"samples_unverified":3,"pointer_only_for_licence":1,"official":{"repos":["ltkong218/ifrnet"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ifrnet-intermediate-feature-refine-network#ran","syntology_url":"https://syntology.ai/paper/2205.14620","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14620"}}}},{"paper":"/paper/masked-conditional-video-diffusion-for","slug":"masked-conditional-video-diffusion-for","title":"MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation","date":"2022-05-19","arxiv_id":"2205.09853","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":7,"samples_constructed":1,"samples_ran_checked":4,"samples_ran_instrument_failed":3,"samples_unverified":9,"pointer_only_for_licence":0,"official":{"repos":["voletiv/mcvd-pytorch"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/masked-conditional-video-diffusion-for#ran","syntology_url":"https://syntology.ai/paper/2205.09853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.09853"}}}},{"paper":"/paper/cross-modal-representation-learning-for-zero","slug":"cross-modal-representation-learning-for-zero","title":"Cross-modal Representation Learning for Zero-shot Action Recognition","date":"2022-05-03","arxiv_id":"2205.01657","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/hybrid-relation-guided-set-matching-for-few","slug":"hybrid-relation-guided-set-matching-for-few","title":"Hybrid Relation Guided Set Matching for Few-shot Action Recognition","date":"2022-04-28","arxiv_id":"2204.13423","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/long-video-generation-with-time-agnostic","slug":"long-video-generation-with-time-agnostic","title":"Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer","date":"2022-04-07","arxiv_id":"2204.03638","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/many-to-many-splatting-for-efficient-video","slug":"many-to-many-splatting-for-efficient-video","title":"Many-to-many Splatting for Efficient Video Frame Interpolation","date":"2022-04-07","arxiv_id":"2204.03513","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/video-diffusion-models","slug":"video-diffusion-models","title":"Video Diffusion Models","date":"2022-04-07","arxiv_id":"2204.03458","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-diffusion-models#ran","syntology_url":"https://syntology.ai/paper/2204.03458","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03458"}}}},{"paper":"/paper/alignment-uniformity-aware-representation","slug":"alignment-uniformity-aware-representation","title":"Alignment-Uniformity aware Representation Learning for Zero-shot Video Classification","date":"2022-03-29","arxiv_id":"2203.15381","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":2,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":5,"official":{"repos":["ShipuLoveMili/CVPR2022-AURL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/alignment-uniformity-aware-representation#ran","syntology_url":"https://syntology.ai/paper/2203.15381","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15381"}}}},{"paper":"/paper/spact-self-supervised-privacy-preservation","slug":"spact-self-supervised-privacy-preservation","title":"SPAct: Self-supervised Privacy Preservation for Action Recognition","date":"2022-03-29","arxiv_id":"2203.15205","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["daveishan/spact"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/spact-self-supervised-privacy-preservation#ran","syntology_url":"https://syntology.ai/paper/2203.15205","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15205"}}}},{"paper":"/paper/rethinking-zero-shot-action-recognition","slug":"rethinking-zero-shot-action-recognition","title":"Rethinking Zero-shot Action Recognition: Learning from Latent Atomic Actions","date":"2022-03-28","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/videomae-masked-autoencoders-are-data-1","slug":"videomae-masked-autoencoders-are-data-1","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","date":"2022-03-23","arxiv_id":"2203.12602","rows_on_this_dataset":2,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":10,"samples_constructed":6,"samples_ran_checked":8,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":12,"official":{"repos":["MCG-NJU/VideoMAE","MCG-NJU/VideoMAE-Action-Detection"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/videomae-masked-autoencoders-are-data-1#ran","syntology_url":"https://syntology.ai/paper/2203.12602","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.12602"}}}},{"paper":"/paper/exploring-motion-ambiguity-and-alignment-for","slug":"exploring-motion-ambiguity-and-alignment-for","title":"Exploring Motion Ambiguity and Alignment for High-Quality Video Frame Interpolation","date":"2022-03-19","arxiv_id":"2203.10291","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/video-gpt-via-next-clip-diffusion","slug":"video-gpt-via-next-clip-diffusion","title":"Video-GPT via Next Clip Diffusion","date":"2025-05-18","arxiv_id":"2505.12489","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mmrl-parameter-efficient-and-interaction","slug":"mmrl-parameter-efficient-and-interaction","title":"MMRL++: Parameter-Efficient and Interaction-Aware Representation Learning for Vision-Language Models","date":"2025-05-15","arxiv_id":"2505.10088","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/ca-2st-cross-attention-in-audio-space-and","slug":"ca-2st-cross-attention-in-audio-space-and","title":"CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition","date":"2025-03-30","arxiv_id":"2503.23447","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/long-context-autoregressive-video-modeling-1","slug":"long-context-autoregressive-video-modeling-1","title":"Long-Context Autoregressive Video Modeling with Next-Frame Prediction","date":"2025-03-25","arxiv_id":"2503.19325","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/leanvae-an-ultra-efficient-reconstruction-vae","slug":"leanvae-an-ultra-efficient-reconstruction-vae","title":"LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion Models","date":"2025-03-18","arxiv_id":"2503.14325","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["westlake-repl/leanvae"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/leanvae-an-ultra-efficient-reconstruction-vae#ran","syntology_url":"https://syntology.ai/paper/2503.14325","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.14325"}}}},{"paper":"/paper/mmrl-multi-modal-representation-learning-for","slug":"mmrl-multi-modal-representation-learning-for","title":"MMRL: Multi-Modal Representation Learning for Vision-Language Models","date":"2025-03-11","arxiv_id":"2503.08497","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["yunncheng/MMRL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mmrl-multi-modal-representation-learning-for#ran","syntology_url":"https://syntology.ai/paper/2503.08497","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.08497"}}}},{"paper":"/paper/label-ranker-self-aware-preference-for","slug":"label-ranker-self-aware-preference-for","title":"Label Ranker: Self-Aware Preference for Classification Label Position in Visual Masked Self-Supervised Pre-Trained Model","date":"2025-03-03","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/acdit-interpolating-autoregressive","slug":"acdit-interpolating-autoregressive","title":"ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer","date":"2024-12-10","arxiv_id":"2412.07720","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["thunlp/acdit"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/acdit-interpolating-autoregressive#ran","syntology_url":"https://syntology.ai/paper/2412.07720","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07720"}}}},{"paper":"/paper/locate-gat-modeling-multi-scale-local-context","slug":"locate-gat-modeling-multi-scale-local-context","title":"LoCATe-GAT: Modeling Multi-Scale Local Context and Action Relationships for Zero-Shot Action Recognition","date":"2024-11-27","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/larp-tokenizing-videos-with-a-learned-1","slug":"larp-tokenizing-videos-with-a-learned-1","title":"LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior","date":"2024-10-28","arxiv_id":"2410.21264","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/larp-tokenizing-videos-with-a-learned-1#ran","syntology_url":"https://syntology.ai/paper/2410.21264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21264"}}}},{"paper":"/paper/hpt-hierarchically-prompting-vision-language","slug":"hpt-hierarchically-prompting-vision-language","title":"HPT++: Hierarchically Prompting Vision-Language Models with Multi-Granularity Knowledge Generation and Improved Structure Modeling","date":"2024-08-27","arxiv_id":"2408.14812","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/vfimamba-video-frame-interpolation-with-state","slug":"vfimamba-video-frame-interpolation-with-state","title":"VFIMamba: Video Frame Interpolation with State Space Models","date":"2024-07-02","arxiv_id":"2407.02315","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":5,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["mcg-nju/vfimamba"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vfimamba-video-frame-interpolation-with-state#ran","syntology_url":"https://syntology.ai/paper/2407.02315","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02315"}}}},{"paper":"/paper/omnitokenizer-a-joint-image-video-tokenizer","slug":"omnitokenizer-a-joint-image-video-tokenizer","title":"OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation","date":"2024-06-13","arxiv_id":"2406.09399","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["foundationvision/omnitokenizer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/omnitokenizer-a-joint-image-video-tokenizer#ran","syntology_url":"https://syntology.ai/paper/2406.09399","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09399"}}}},{"paper":"/paper/hierarchical-patch-diffusion-models-for-high-1","slug":"hierarchical-patch-diffusion-models-for-high-1","title":"Hierarchical Patch Diffusion Models for High-Resolution Video Generation","date":"2024-06-12","arxiv_id":"2406.07792","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/let-go-of-your-labels-with-unsupervised-1","slug":"let-go-of-your-labels-with-unsupervised-1","title":"Let Go of Your Labels with Unsupervised Transfer","date":"2024-06-11","arxiv_id":"2406.07236","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":4,"official":{"repos":["mlbio-epfl/turtle"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/let-go-of-your-labels-with-unsupervised-1#ran","syntology_url":"https://syntology.ai/paper/2406.07236","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07236"}}}},{"paper":"/paper/fifo-diffusion-generating-infinite-videos","slug":"fifo-diffusion-generating-infinite-videos","title":"FIFO-Diffusion: Generating Infinite Videos from Text without Training","date":"2024-05-19","arxiv_id":"2405.11473","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":5,"samples_unverified":3,"pointer_only_for_licence":13,"official":{"repos":["jjihwan/FIFO-Diffusion_public"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/fifo-diffusion-generating-infinite-videos#ran","syntology_url":"https://syntology.ai/paper/2405.11473","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.11473"}}}},{"paper":"/paper/leveraging-temporal-contextualization-for","slug":"leveraging-temporal-contextualization-for","title":"Leveraging Temporal Contextualization for Video Action Recognition","date":"2024-04-15","arxiv_id":"2404.09490","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":4,"official":{"repos":["naver-ai/tc-clip"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/leveraging-temporal-contextualization-for#ran","syntology_url":"https://syntology.ai/paper/2404.09490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09490"}}}},{"paper":"/paper/label-propagation-for-zero-shot","slug":"label-propagation-for-zero-shot","title":"Label Propagation for Zero-shot Classification with Vision-Language Models","date":"2024-04-05","arxiv_id":"2404.04072","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["vladan-stojnic/zlap"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/label-propagation-for-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2404.04072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04072"}}}},{"paper":"/paper/prompt-learning-via-meta-regularization","slug":"prompt-learning-via-meta-regularization","title":"Prompt Learning via Meta-Regularization","date":"2024-04-01","arxiv_id":"2404.00851","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":2,"official":{"repos":["mlvlab/prometar"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/prompt-learning-via-meta-regularization#ran","syntology_url":"https://syntology.ai/paper/2404.00851","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00851"}}}},{"paper":"/paper/grid-diffusion-models-for-text-to-video-1","slug":"grid-diffusion-models-for-text-to-video-1","title":"Grid Diffusion Models for Text-to-Video Generation","date":"2024-03-30","arxiv_id":"2404.00234","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/enhancing-video-transformers-for-action","slug":"enhancing-video-transformers-for-action","title":"Enhancing Video Transformers for Action Understanding with VLM-aided Training","date":"2024-03-24","arxiv_id":"2403.16128","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/promptkd-unsupervised-prompt-distillation-for","slug":"promptkd-unsupervised-prompt-distillation-for","title":"PromptKD: Unsupervised Prompt Distillation for Vision-Language Models","date":"2024-03-05","arxiv_id":"2403.02781","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/snap-video-scaled-spatiotemporal-transformers","slug":"snap-video-scaled-spatiotemporal-transformers","title":"Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis","date":"2024-02-22","arxiv_id":"2402.14797","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/video-lavit-unified-video-language-pre","slug":"video-lavit-unified-video-language-pre","title":"Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization","date":"2024-02-05","arxiv_id":"2402.03161","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":5,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-lavit-unified-video-language-pre#ran","syntology_url":"https://syntology.ai/paper/2402.03161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03161"}}}},{"paper":"/paper/lumiere-a-space-time-diffusion-model-for","slug":"lumiere-a-space-time-diffusion-model-for","title":"Lumiere: A Space-Time Diffusion Model for Video Generation","date":"2024-01-23","arxiv_id":"2401.12945","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/lumiere-a-space-time-diffusion-model-for#ran","syntology_url":"https://syntology.ai/paper/2401.12945","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.12945"}}}},{"paper":"/paper/omnivec2-a-novel-transformer-based-network","slug":"omnivec2-a-novel-transformer-based-network","title":"OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","date":"2024-01-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/videopoet-a-large-language-model-for-zero","slug":"videopoet-a-large-language-model-for-zero","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","date":"2023-12-21","arxiv_id":"2312.14125","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/ez-clip-efficient-zeroshot-video-action","slug":"ez-clip-efficient-zeroshot-video-action","title":"EZ-CLIP: Efficient Zeroshot Video Action Recognition","date":"2023-12-13","arxiv_id":"2312.08010","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":9,"samples_unverified":4,"pointer_only_for_licence":4,"official":{"repos":["shahzadnit/ez-clip"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ez-clip-efficient-zeroshot-video-action#ran","syntology_url":"https://syntology.ai/paper/2312.08010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.08010"}}}},{"paper":"/paper/learning-hierarchical-prompt-with-structured","slug":"learning-hierarchical-prompt-with-structured","title":"Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models","date":"2023-12-11","arxiv_id":"2312.06323","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":5,"official":{"repos":["vill-lab/2024-aaai-hpt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-hierarchical-prompt-with-structured#ran","syntology_url":"https://syntology.ai/paper/2312.06323","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06323"}}}},{"paper":"/paper/photorealistic-video-generation-with","slug":"photorealistic-video-generation-with","title":"Photorealistic Video Generation with Diffusion Models","date":"2023-12-11","arxiv_id":"2312.06662","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/ost-refining-text-knowledge-with-optimal","slug":"ost-refining-text-knowledge-with-optimal","title":"OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition","date":"2023-11-30","arxiv_id":"2312.00096","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["tomchen-ctj/OST"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ost-refining-text-knowledge-with-optimal#ran","syntology_url":"https://syntology.ai/paper/2312.00096","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00096"}}}},{"paper":"/paper/videoassembler-identity-consistent-video","slug":"videoassembler-identity-consistent-video","title":"MagDiff: Multi-Alignment Diffusion for High-Fidelity Video Generation and Editing","date":"2023-11-29","arxiv_id":"2311.17338","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":12,"official":{"repos":["gulucaptain/videoassembler"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/videoassembler-identity-consistent-video#ran","syntology_url":"https://syntology.ai/paper/2311.17338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17338"}}}},{"paper":"/paper/make-pixels-dance-high-dynamic-video","slug":"make-pixels-dance-high-dynamic-video","title":"Make Pixels Dance: High-Dynamic Video Generation","date":"2023-11-18","arxiv_id":"2311.10982","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/omnivec-learning-robust-representations-with","slug":"omnivec-learning-robust-representations-with","title":"OmniVec: Learning robust representations with cross modal sharing","date":"2023-11-07","arxiv_id":"2311.05709","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/asymmetric-masked-distillation-for-pre","slug":"asymmetric-masked-distillation-for-pre","title":"Asymmetric Masked Distillation for Pre-Training Small Foundation Models","date":"2023-11-06","arxiv_id":"2311.03149","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/regis-refining-generated-videos-via-iterative","slug":"regis-refining-generated-videos-via-iterative","title":"REGIS: Refining Generated Videos via Iterative Stylistic Redesigning","date":"2023-11-03","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/image-clustering-with-external-guidance","slug":"image-clustering-with-external-guidance","title":"Image Clustering with External Guidance","date":"2023-10-18","arxiv_id":"2310.11989","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":9,"official":{"repos":["xlearning-scu/2024-icml-tac"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/image-clustering-with-external-guidance#ran","syntology_url":"https://syntology.ai/paper/2310.11989","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.11989"}}}},{"paper":"/paper/language-model-beats-diffusion-tokenizer-is","slug":"language-model-beats-diffusion-tokenizer-is","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","date":"2023-10-09","arxiv_id":"2310.05737","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":20,"samples_ran":19,"samples_constructed":0,"samples_ran_checked":14,"samples_ran_instrument_failed":5,"samples_unverified":1,"pointer_only_for_licence":5,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/language-model-beats-diffusion-tokenizer-is#ran","syntology_url":"https://syntology.ai/paper/2310.05737","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05737"}}}},{"paper":"/paper/zeroi2v-zero-cost-adaptation-of-pre-trained","slug":"zeroi2v-zero-cost-adaptation-of-pre-trained","title":"ZeroI2V: Zero-Cost Adaptation of Pre-trained Transformers from Image to Video","date":"2023-10-02","arxiv_id":"2310.01324","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["mcg-nju/zeroi2v","leexinhao/ZeroI2V"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/zeroi2v-zero-cost-adaptation-of-pre-trained#ran","syntology_url":"https://syntology.ai/paper/2310.01324","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01324"}}}},{"paper":"/paper/lavie-high-quality-video-generation-with","slug":"lavie-high-quality-video-generation-with","title":"LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models","date":"2023-09-26","arxiv_id":"2309.15103","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["Vchitect/LaVie"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/lavie-high-quality-video-generation-with#ran","syntology_url":"https://syntology.ai/paper/2309.15103","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.15103"}}}},{"paper":"/paper/dept-decoupled-prompt-tuning","slug":"dept-decoupled-prompt-tuning","title":"DePT: Decoupled Prompt Tuning","date":"2023-09-14","arxiv_id":"2309.07439","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":4,"pointer_only_for_licence":8,"official":{"repos":["koorye/dept"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/dept-decoupled-prompt-tuning#ran","syntology_url":"https://syntology.ai/paper/2309.07439","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07439"}}}},{"paper":"/paper/read-only-prompt-optimization-for-vision","slug":"read-only-prompt-optimization-for-vision","title":"Read-only Prompt Optimization for Vision-Language Few-shot Learning","date":"2023-08-29","arxiv_id":"2308.14960","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["mlvlab/rpo"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/read-only-prompt-optimization-for-vision#ran","syntology_url":"https://syntology.ai/paper/2308.14960","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.14960"}}}},{"paper":"/paper/orthogonal-temporal-interpolation-for-zero","slug":"orthogonal-temporal-interpolation-for-zero","title":"Orthogonal Temporal Interpolation for Zero-Shot Video Recognition","date":"2023-08-14","arxiv_id":"2308.06897","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["sweetorangezhuyan/mm2023_oti"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/orthogonal-temporal-interpolation-for-zero#ran","syntology_url":"https://syntology.ai/paper/2308.06897","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06897"}}}},{"paper":"/paper/self-regulating-prompts-foundational-model","slug":"self-regulating-prompts-foundational-model","title":"Self-regulating Prompts: Foundational Model Adaptation without Forgetting","date":"2023-07-13","arxiv_id":"2307.06948","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":17,"samples_constructed":0,"samples_ran_checked":12,"samples_ran_instrument_failed":5,"samples_unverified":4,"pointer_only_for_licence":3,"official":{"repos":["muzairkhattak/promptsrc"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/self-regulating-prompts-foundational-model#ran","syntology_url":"https://syntology.ai/paper/2307.06948","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.06948"}}}},{"paper":"/paper/benchmarking-self-supervised-video","slug":"benchmarking-self-supervised-video","title":"A Large-Scale Analysis on Self-Supervised Video Representation Learning","date":"2023-06-09","arxiv_id":"2306.06010","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/consistency-guided-prompt-learning-for-vision","slug":"consistency-guided-prompt-learning-for-vision","title":"Consistency-guided Prompt Learning for Vision-Language Models","date":"2023-06-01","arxiv_id":"2306.01195","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":4,"official":{"repos":["shuvenduroy/coprompt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/consistency-guided-prompt-learning-for-vision#ran","syntology_url":"https://syntology.ai/paper/2306.01195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.01195"}}}},{"paper":"/paper/preserve-your-own-correlation-a-noise-prior","slug":"preserve-your-own-correlation-a-noise-prior","title":"Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models","date":"2023-05-17","arxiv_id":"2305.10474","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/alternating-gradient-descent-and-mixture-of","slug":"alternating-gradient-descent-and-mixture-of","title":"Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception","date":"2023-05-10","arxiv_id":"2305.06324","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/video-frame-interpolation-with-densely","slug":"video-frame-interpolation-with-densely","title":"Video Frame Interpolation with Densely Queried Bilateral Correlation","date":"2023-04-26","arxiv_id":"2304.13596","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["kinoud/DQBC"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-frame-interpolation-with-densely#ran","syntology_url":"https://syntology.ai/paper/2304.13596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.13596"}}}},{"paper":"/paper/align-your-latents-high-resolution-video","slug":"align-your-latents-high-resolution-video","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","date":"2023-04-18","arxiv_id":"2304.08818","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":26,"samples_ran":18,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":9,"samples_unverified":8,"pointer_only_for_licence":3,"official":{"repos":["stability-ai/generative-models"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/align-your-latents-high-resolution-video#ran","syntology_url":"https://syntology.ai/paper/2304.08818","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.08818"}}}},{"paper":"/paper/synthetic-sample-selection-for-generalized","slug":"synthetic-sample-selection-for-generalized","title":"Synthetic Sample Selection for Generalized Zero-Shot Learning","date":"2023-04-06","arxiv_id":"2304.02846","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/victr-video-conditioned-text-representations","slug":"victr-video-conditioned-text-representations","title":"VicTR: Video-conditioned Text Representations for Activity Recognition","date":"2023-04-05","arxiv_id":"2304.02560","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/videomae-v2-scaling-video-masked-autoencoders","slug":"videomae-v2-scaling-video-masked-autoencoders","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","date":"2023-03-29","arxiv_id":"2303.16727","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["OpenGVLab/VideoMAEv2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/videomae-v2-scaling-video-masked-autoencoders#ran","syntology_url":"https://syntology.ai/paper/2303.16727","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16727"}}}},{"paper":"/paper/eva-clip-improved-training-techniques-for","slug":"eva-clip-improved-training-techniques-for","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","date":"2023-03-27","arxiv_id":"2303.15389","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["baaivision/eva"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/eva-clip-improved-training-techniques-for#ran","syntology_url":"https://syntology.ai/paper/2303.15389","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.15389"}}}},{"paper":"/paper/unified-keypoint-based-action-recognition","slug":"unified-keypoint-based-action-recognition","title":"Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling","date":"2023-03-27","arxiv_id":"2303.15270","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/towards-end-to-end-generative-modeling-of","slug":"towards-end-to-end-generative-modeling-of","title":"Towards End-to-End Generative Modeling of Long Videos with Memory-Efficient Bidirectional Transformers","date":"2023-03-20","arxiv_id":"2303.11251","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/decomposed-diffusion-models-for-high-quality","slug":"decomposed-diffusion-models-for-high-quality","title":"VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation","date":"2023-03-15","arxiv_id":"2303.08320","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/match-expand-and-improve-unsupervised","slug":"match-expand-and-improve-unsupervised","title":"MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge","date":"2023-03-15","arxiv_id":"2303.08914","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":4,"official":{"repos":["wlin-at/maxi"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/match-expand-and-improve-unsupervised#ran","syntology_url":"https://syntology.ai/paper/2303.08914","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08914"}}}},{"paper":"/paper/extracting-motion-and-appearance-via-inter","slug":"extracting-motion-and-appearance-via-inter","title":"Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation","date":"2023-03-01","arxiv_id":"2303.00440","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":10,"samples_constructed":5,"samples_ran_checked":6,"samples_ran_instrument_failed":4,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["mcg-nju/ema-vfi"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/extracting-motion-and-appearance-via-inter#ran","syntology_url":"https://syntology.ai/paper/2303.00440","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.00440"}}}},{"paper":"/paper/video-action-recognition-collaborative","slug":"video-action-recognition-collaborative","title":"Video Action Recognition Collaborative Learning with Dynamics via PSO-ConvNet Transformer","date":"2023-02-17","arxiv_id":"2302.09187","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/bidirectional-cross-modal-knowledge","slug":"bidirectional-cross-modal-knowledge","title":"Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models","date":"2022-12-31","arxiv_id":"2301.00182","rows_on_this_dataset":2,"code_links":5,"syntology":null},{"paper":"/paper/adaptive-frame-selection-in-two-dimensional","slug":"adaptive-frame-selection-in-two-dimensional","title":"Adaptive frame selection in two dimensional convolutional neural network action recognition","date":"2022-12-28","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/similarity-contrastive-estimation-for-image","slug":"similarity-contrastive-estimation-for-image","title":"Similarity Contrastive Estimation for Image and Video Soft Contrastive Self-Supervised Learning","date":"2022-12-21","arxiv_id":"2212.11187","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/magvit-masked-generative-video-transformer","slug":"magvit-masked-generative-video-transformer","title":"MAGVIT: Masked Generative Video Transformer","date":"2022-12-10","arxiv_id":"2212.05199","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["google-research/magvit"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/magvit-masked-generative-video-transformer#ran","syntology_url":"https://syntology.ai/paper/2212.05199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.05199"}}}},{"paper":"/paper/video-text-modeling-with-zero-shot-transfer","slug":"video-text-modeling-with-zero-shot-transfer","title":"VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners","date":"2022-12-09","arxiv_id":"2212.04979","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-domain-invariant-prompt-for-vision","slug":"learning-domain-invariant-prompt-for-vision","title":"Learning Domain Invariant Prompt for Vision-Language Models","date":"2022-12-08","arxiv_id":"2212.04196","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/masked-video-distillation-rethinking-masked","slug":"masked-video-distillation-rethinking-masked","title":"Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning","date":"2022-12-08","arxiv_id":"2212.04500","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/internvideo-general-video-foundation-models","slug":"internvideo-general-video-foundation-models","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","date":"2022-12-06","arxiv_id":"2212.03191","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["opengvlab/internvideo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/internvideo-general-video-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2212.03191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03191"}}}},{"paper":"/paper/vidm-video-implicit-diffusion-models","slug":"vidm-video-implicit-diffusion-models","title":"VIDM: Video Implicit Diffusion Models","date":"2022-12-01","arxiv_id":"2212.00235","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["MKFMIKU/VIDM"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vidm-video-implicit-diffusion-models#ran","syntology_url":"https://syntology.ai/paper/2212.00235","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.00235"}}}},{"paper":"/paper/xkd-cross-modal-knowledge-distillation-with","slug":"xkd-cross-modal-knowledge-distillation-with","title":"XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning","date":"2022-11-25","arxiv_id":"2211.13929","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/latent-video-diffusion-models-for-high","slug":"latent-video-diffusion-models-for-high","title":"Latent Video Diffusion Models for High-Fidelity Long Video Generation","date":"2022-11-23","arxiv_id":"2211.13221","rows_on_this_dataset":5,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":13,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":7,"samples_unverified":1,"pointer_only_for_licence":5,"official":{"repos":["yingqinghe/lvdm"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/latent-video-diffusion-models-for-high#ran","syntology_url":"https://syntology.ai/paper/2211.13221","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.13221"}}}},{"paper":"/paper/tell-me-what-happened-unifying-text-guided","slug":"tell-me-what-happened-unifying-text-guided","title":"Tell Me What Happened: Unifying Text-guided Video Completion via Multimodal Masked Video Generation","date":"2022-11-23","arxiv_id":"2211.12824","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/magicvideo-efficient-video-generation-with","slug":"magicvideo-efficient-video-generation-with","title":"MagicVideo: Efficient Video Generation With Latent Diffusion Models","date":"2022-11-20","arxiv_id":"2211.11018","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/efficient-video-representation-learning-via","slug":"efficient-video-representation-learning-via","title":"EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens","date":"2022-11-19","arxiv_id":"2211.10636","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":3,"samples_constructed":3,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":6,"official":{"repos":["sunilhoho/everest","sunilhoho/VideoMS"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/efficient-video-representation-learning-via#ran","syntology_url":"https://syntology.ai/paper/2211.10636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.10636"}}}},{"paper":"/paper/a-unified-pyramid-recurrent-network-for-video","slug":"a-unified-pyramid-recurrent-network-for-video","title":"A Unified Pyramid Recurrent Network for Video Frame Interpolation","date":"2022-11-07","arxiv_id":"2211.03456","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/m-3-video-masked-motion-modeling-for-self","slug":"m-3-video-masked-motion-modeling-for-self","title":"Masked Motion Encoding for Self-Supervised Video Representation Learning","date":"2022-10-12","arxiv_id":"2210.06096","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/maple-multi-modal-prompt-learning","slug":"maple-multi-modal-prompt-learning","title":"MaPLe: Multi-modal Prompt Learning","date":"2022-10-06","arxiv_id":"2210.03117","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["muzairkhattak/multimodal-prompt-learning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/maple-multi-modal-prompt-learning#ran","syntology_url":"https://syntology.ai/paper/2210.03117","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03117"}}}},{"paper":"/paper/variational-prompt-tuning-improves","slug":"variational-prompt-tuning-improves","title":"Bayesian Prompt Learning for Image-Language Model Generalization","date":"2022-10-05","arxiv_id":"2210.02390","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":3,"official":{"repos":["saic-fi/bayesian-prompt-learning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/variational-prompt-tuning-improves#ran","syntology_url":"https://syntology.ai/paper/2210.02390","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.02390"}}}},{"paper":"/paper/make-a-video-text-to-video-generation-without","slug":"make-a-video-text-to-video-generation-without","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","date":"2022-09-29","arxiv_id":"2209.14792","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/expanding-language-image-pretrained-models","slug":"expanding-language-image-pretrained-models","title":"Expanding Language-Image Pretrained Models for General Video Recognition","date":"2022-08-04","arxiv_id":"2208.02816","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":3,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["microsoft/videox"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/expanding-language-image-pretrained-models#ran","syntology_url":"https://syntology.ai/paper/2208.02816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.02816"}}}},{"paper":"/paper/multimodal-open-vocabulary-video","slug":"multimodal-open-vocabulary-video","title":"Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models","date":"2022-07-15","arxiv_id":"2207.07646","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/neighbor-correspondence-matching-for-flow","slug":"neighbor-correspondence-matching-for-flow","title":"Neighbor Correspondence Matching for Flow-based Video Frame Synthesis","date":"2022-07-14","arxiv_id":"2207.06763","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/federated-self-supervised-learning-for-video","slug":"federated-self-supervised-learning-for-video","title":"Federated Self-supervised Learning for Video Understanding","date":"2022-07-05","arxiv_id":"2207.01975","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/transferring-textual-knowledge-for-visual","slug":"transferring-textual-knowledge-for-visual","title":"Revisiting Classifier: Transferring Vision-Language Models for Video Recognition","date":"2022-07-04","arxiv_id":"2207.01297","rows_on_this_dataset":2,"code_links":5,"syntology":null},{"paper":"/paper/slic-self-supervised-learning-with-iterative-1","slug":"slic-self-supervised-learning-with-iterative-1","title":"SLIC: Self-Supervised Learning with Iterative Clustering for Human Action Videos","date":"2022-06-25","arxiv_id":"2206.12534","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/enhanced-bi-directional-motion-estimation-for","slug":"enhanced-bi-directional-motion-estimation-for","title":"Enhanced Bi-directional Motion Estimation for Video Frame Interpolation","date":"2022-06-17","arxiv_id":"2206.08572","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learn2augment-learning-to-composite-videos","slug":"learn2augment-learning-to-composite-videos","title":"Learn2Augment: Learning to Composite Videos for Data Augmentation in Action Recognition","date":"2022-06-09","arxiv_id":"2206.04790","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/cogvideo-large-scale-pretraining-for-text-to","slug":"cogvideo-large-scale-pretraining-for-text-to","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","date":"2022-05-29","arxiv_id":"2205.15868","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/ifrnet-intermediate-feature-refine-network","slug":"ifrnet-intermediate-feature-refine-network","title":"IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation","date":"2022-05-29","arxiv_id":"2205.14620","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":20,"samples_ran":17,"samples_constructed":2,"samples_ran_checked":13,"samples_ran_instrument_failed":4,"samples_unverified":3,"pointer_only_for_licence":1,"official":{"repos":["ltkong218/ifrnet"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ifrnet-intermediate-feature-refine-network#ran","syntology_url":"https://syntology.ai/paper/2205.14620","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14620"}}}},{"paper":"/paper/masked-conditional-video-diffusion-for","slug":"masked-conditional-video-diffusion-for","title":"MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation","date":"2022-05-19","arxiv_id":"2205.09853","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":7,"samples_constructed":1,"samples_ran_checked":4,"samples_ran_instrument_failed":3,"samples_unverified":9,"pointer_only_for_licence":0,"official":{"repos":["voletiv/mcvd-pytorch"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/masked-conditional-video-diffusion-for#ran","syntology_url":"https://syntology.ai/paper/2205.09853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.09853"}}}},{"paper":"/paper/cross-modal-representation-learning-for-zero","slug":"cross-modal-representation-learning-for-zero","title":"Cross-modal Representation Learning for Zero-shot Action Recognition","date":"2022-05-03","arxiv_id":"2205.01657","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/hybrid-relation-guided-set-matching-for-few","slug":"hybrid-relation-guided-set-matching-for-few","title":"Hybrid Relation Guided Set Matching for Few-shot Action Recognition","date":"2022-04-28","arxiv_id":"2204.13423","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/long-video-generation-with-time-agnostic","slug":"long-video-generation-with-time-agnostic","title":"Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer","date":"2022-04-07","arxiv_id":"2204.03638","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/many-to-many-splatting-for-efficient-video","slug":"many-to-many-splatting-for-efficient-video","title":"Many-to-many Splatting for Efficient Video Frame Interpolation","date":"2022-04-07","arxiv_id":"2204.03513","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/video-diffusion-models","slug":"video-diffusion-models","title":"Video Diffusion Models","date":"2022-04-07","arxiv_id":"2204.03458","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-diffusion-models#ran","syntology_url":"https://syntology.ai/paper/2204.03458","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03458"}}}},{"paper":"/paper/alignment-uniformity-aware-representation","slug":"alignment-uniformity-aware-representation","title":"Alignment-Uniformity aware Representation Learning for Zero-shot Video Classification","date":"2022-03-29","arxiv_id":"2203.15381","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":2,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":5,"official":{"repos":["ShipuLoveMili/CVPR2022-AURL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/alignment-uniformity-aware-representation#ran","syntology_url":"https://syntology.ai/paper/2203.15381","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15381"}}}},{"paper":"/paper/spact-self-supervised-privacy-preservation","slug":"spact-self-supervised-privacy-preservation","title":"SPAct: Self-supervised Privacy Preservation for Action Recognition","date":"2022-03-29","arxiv_id":"2203.15205","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["daveishan/spact"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/spact-self-supervised-privacy-preservation#ran","syntology_url":"https://syntology.ai/paper/2203.15205","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15205"}}}},{"paper":"/paper/rethinking-zero-shot-action-recognition","slug":"rethinking-zero-shot-action-recognition","title":"Rethinking Zero-shot Action Recognition: Learning from Latent Atomic Actions","date":"2022-03-28","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/videomae-masked-autoencoders-are-data-1","slug":"videomae-masked-autoencoders-are-data-1","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","date":"2022-03-23","arxiv_id":"2203.12602","rows_on_this_dataset":2,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":10,"samples_constructed":6,"samples_ran_checked":8,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":12,"official":{"repos":["MCG-NJU/VideoMAE","MCG-NJU/VideoMAE-Action-Detection"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/videomae-masked-autoencoders-are-data-1#ran","syntology_url":"https://syntology.ai/paper/2203.12602","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.12602"}}}},{"paper":"/paper/exploring-motion-ambiguity-and-alignment-for","slug":"exploring-motion-ambiguity-and-alignment-for","title":"Exploring Motion Ambiguity and Alignment for High-Quality Video Frame Interpolation","date":"2022-03-19","arxiv_id":"2203.10291","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/conditional-prompt-learning-for-vision","slug":"conditional-prompt-learning-for-vision","title":"Conditional Prompt Learning for Vision-Language Models","date":"2022-03-10","arxiv_id":"2203.05557","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":3,"official":{"repos":["kaiyangzhou/coop"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/conditional-prompt-learning-for-vision#ran","syntology_url":"https://syntology.ai/paper/2203.05557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.05557"}}}},{"paper":"/paper/learning-cross-video-neural-representations","slug":"learning-cross-video-neural-representations","title":"Learning Cross-Video Neural Representations for High-Quality Frame Interpolation","date":"2022-02-28","arxiv_id":"2203.00137","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["wustl-cig/CURE"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-cross-video-neural-representations#ran","syntology_url":"https://syntology.ai/paper/2203.00137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.00137"}}}},{"paper":"/paper/generating-videos-with-dynamics-aware-1","slug":"generating-videos-with-dynamics-aware-1","title":"Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks","date":"2022-02-21","arxiv_id":"2202.10571","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/film-frame-interpolation-for-large-motion","slug":"film-frame-interpolation-for-large-motion","title":"FILM: Frame Interpolation for Large Motion","date":"2022-02-10","arxiv_id":"2202.04901","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":20,"samples_ran":12,"samples_constructed":6,"samples_ran_checked":9,"samples_ran_instrument_failed":3,"samples_unverified":8,"pointer_only_for_licence":0,"official":{"repos":["google-research/frame-interpolation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/film-frame-interpolation-for-large-motion#ran","syntology_url":"https://syntology.ai/paper/2202.04901","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.04901"}}}},{"paper":"/paper/spatio-temporal-relation-modeling-for-few","slug":"spatio-temporal-relation-modeling-for-few","title":"Spatio-temporal Relation Modeling for Few-shot Action Recognition","date":"2021-12-09","arxiv_id":"2112.05132","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/self-supervised-video-transformer","slug":"self-supervised-video-transformer","title":"Self-supervised Video Transformer","date":"2021-12-02","arxiv_id":"2112.01514","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["kahnchana/svt"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/self-supervised-video-transformer#ran","syntology_url":"https://syntology.ai/paper/2112.01514","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.01514"}}}},{"paper":"/paper/spatio-temporal-multi-flow-network-for-video","slug":"spatio-temporal-multi-flow-network-for-video","title":"ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation","date":"2021-11-30","arxiv_id":"2111.15483","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/self-supervised-audio-visual-representation","slug":"self-supervised-audio-visual-representation","title":"Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity","date":"2021-11-09","arxiv_id":"2111.05329","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/efficient-action-recognition-using-confidence","slug":"efficient-action-recognition-using-confidence","title":"Efficient Action Recognition Using Confidence Distillation","date":"2021-09-05","arxiv_id":"2109.02137","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/ligar-lightweight-general-purpose-action","slug":"ligar-lightweight-general-purpose-action","title":"LIGAR: Lightweight General-purpose Action Recognition","date":"2021-08-30","arxiv_id":"2108.13153","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/self-supervised-video-representation-learning-8","slug":"self-supervised-video-representation-learning-8","title":"Self-Supervised Video Representation Learning with Meta-Contrastive Network","date":"2021-08-19","arxiv_id":"2108.08426","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/asymmetric-bilateral-motion-estimation-for","slug":"asymmetric-bilateral-motion-estimation-for","title":"Asymmetric Bilateral Motion Estimation for Video Frame Interpolation","date":"2021-08-15","arxiv_id":"2108.06815","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":2,"official":{"repos":["junheum/abme"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/asymmetric-bilateral-motion-estimation-for#ran","syntology_url":"https://syntology.ai/paper/2108.06815","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.06815"}}}},{"paper":"/paper/elaborative-rehearsal-for-zero-shot-action","slug":"elaborative-rehearsal-for-zero-shot-action","title":"Elaborative Rehearsal for Zero-shot Action Recognition","date":"2021-08-05","arxiv_id":"2108.02833","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":2,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["DeLightCMU/ElaborativeRehearsal"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/elaborative-rehearsal-for-zero-shot-action#ran","syntology_url":"https://syntology.ai/paper/2108.02833","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.02833"}}}},{"paper":"/paper/vimpac-video-pre-training-via-masked-token","slug":"vimpac-video-pre-training-via-masked-token","title":"VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning","date":"2021-06-21","arxiv_id":"2106.11250","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["airsplay/vimpac"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vimpac-video-pre-training-via-masked-token#ran","syntology_url":"https://syntology.ai/paper/2106.11250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11250"}}}},{"paper":"/paper/self-supervised-video-representation-learning-7","slug":"self-supervised-video-representation-learning-7","title":"Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting","date":"2021-06-18","arxiv_id":"2106.10137","rows_on_this_dataset":9,"code_links":1,"syntology":null},{"paper":"/paper/a-good-image-generator-is-what-you-need-for-1","slug":"a-good-image-generator-is-what-you-need-for-1","title":"A Good Image Generator Is What You Need for High-Resolution Video Synthesis","date":"2021-04-30","arxiv_id":"2104.15069","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-large-scale-study-on-unsupervised","slug":"a-large-scale-study-on-unsupervised","title":"A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning","date":"2021-04-29","arxiv_id":"2104.14558","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/vidtr-video-transformer-without-convolutions","slug":"vidtr-video-transformer-without-convolutions","title":"VidTr: Video Transformer Without Convolutions","date":"2021-04-23","arxiv_id":"2104.11746","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/videogpt-video-generation-using-vq-vae-and","slug":"videogpt-video-generation-using-vq-vae-and","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","date":"2021-04-20","arxiv_id":"2104.10157","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/broaden-your-views-for-self-supervised-video","slug":"broaden-your-views-for-self-supervised-video","title":"Broaden Your Views for Self-Supervised Video Learning","date":"2021-03-30","arxiv_id":"2103.16559","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["deepmind/brave"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/broaden-your-views-for-self-supervised-video#ran","syntology_url":"https://syntology.ai/paper/2103.16559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.16559"}}}},{"paper":"/paper/video-classification-with-finecoarse-networks","slug":"video-classification-with-finecoarse-networks","title":"Busy-Quiet Video Disentangling for Video Classification","date":"2021-03-29","arxiv_id":"2103.15584","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/an-image-is-worth-16x16-words-what-is-a-video","slug":"an-image-is-worth-16x16-words-what-is-a-video","title":"An Image is Worth 16x16 Words, What is a Video Worth?","date":"2021-03-25","arxiv_id":"2103.13915","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["Alibaba-MIIL/STAM"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/an-image-is-worth-16x16-words-what-is-a-video#ran","syntology_url":"https://syntology.ai/paper/2103.13915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13915"}}}},{"paper":"/paper/cdfi-compression-driven-network-design-for","slug":"cdfi-compression-driven-network-design-for","title":"CDFI: Compression-Driven Network Design for Frame Interpolation","date":"2021-03-18","arxiv_id":"2103.10559","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/videomoco-contrastive-video-representation","slug":"videomoco-contrastive-video-representation","title":"VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples","date":"2021-03-10","arxiv_id":"2103.05905","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["tinapan-pt/VideoMoCo"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/videomoco-contrastive-video-representation#ran","syntology_url":"https://syntology.ai/paper/2103.05905","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.05905"}}}},{"paper":"/paper/learning-transferable-visual-models-from","slug":"learning-transferable-visual-models-from","title":"Learning Transferable Visual Models From Natural Language Supervision","date":"2021-02-26","arxiv_id":"2103.00020","rows_on_this_dataset":1,"code_links":82,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":20,"samples_ran":16,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":14,"samples_unverified":4,"pointer_only_for_licence":16,"official":{"repos":["openai/CLIP"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-transferable-visual-models-from#ran","syntology_url":"https://syntology.ai/paper/2103.00020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.00020"}}}},{"paper":"/paper/tclr-temporal-contrastive-learning-for-video","slug":"tclr-temporal-contrastive-learning-for-video","title":"TCLR: Temporal Contrastive Learning for Video Representation","date":"2021-01-20","arxiv_id":"2101.07974","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["DAVEISHAN/TCLR"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tclr-temporal-contrastive-learning-for-video#ran","syntology_url":"https://syntology.ai/paper/2101.07974","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.07974"}}}},{"paper":"/paper/claster-clustering-with-reinforcement","slug":"claster-clustering-with-reinforcement","title":"CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition","date":"2021-01-18","arxiv_id":"2101.07042","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/temporal-relational-crosstransformers-for-few","slug":"temporal-relational-crosstransformers-for-few","title":"Temporal-Relational CrossTransformers for Few-Shot Action Recognition","date":"2021-01-15","arxiv_id":"2101.06184","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":2,"samples_constructed":1,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":1,"official":{"repos":["tobyperrett/trx"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/temporal-relational-crosstransformers-for-few#ran","syntology_url":"https://syntology.ai/paper/2101.06184","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.06184"}}}},{"paper":"/paper/smart-frame-selection-for-action-recognition","slug":"smart-frame-selection-for-action-recognition","title":"SMART Frame Selection for Action Recognition","date":"2020-12-19","arxiv_id":"2012.10671","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/latent-neural-differential-equations-for","slug":"latent-neural-differential-equations-for","title":"Latent Neural Differential Equations for Video Generation","date":"2020-11-07","arxiv_id":"2011.03864","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["Zasder3/Latent-Neural-Differential-Equations-for-Video-Generation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/latent-neural-differential-equations-for#ran","syntology_url":"https://syntology.ai/paper/2011.03864","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.03864"}}}},{"paper":"/paper/bubblenet-a-disperse-recurrent-structure-to","slug":"bubblenet-a-disperse-recurrent-structure-to","title":"Bubblenet: A Disperse Recurrent Structure To Recognize Activities","date":"2020-10-30","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/self-supervised-video-representation-using","slug":"self-supervised-video-representation-using","title":"Pretext-Contrastive Learning: Toward Good Practices in Self-supervised Video Representation Leaning","date":"2020-10-29","arxiv_id":"2010.15464","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rspnet-relative-speed-perception-for","slug":"rspnet-relative-speed-perception-for","title":"RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning","date":"2020-10-27","arxiv_id":"2011.07949","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/depth-guided-adaptive-meta-fusion-network-for","slug":"depth-guided-adaptive-meta-fusion-network-for","title":"Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition","date":"2020-10-20","arxiv_id":"2010.09982","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["lovelyqian/AMeFu-Net"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/depth-guided-adaptive-meta-fusion-network-for#ran","syntology_url":"https://syntology.ai/paper/2010.09982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.09982"}}}},{"paper":"/paper/self-supervised-co-training-for-video","slug":"self-supervised-co-training-for-video","title":"Self-supervised Co-training for Video Representation Learning","date":"2020-10-19","arxiv_id":"2010.09709","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["TengdaHan/CoCLR"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/self-supervised-co-training-for-video#ran","syntology_url":"https://syntology.ai/paper/2010.09709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.09709"}}}},{"paper":"/paper/perf-net-pose-empowered-rgb-flow-net","slug":"perf-net-pose-empowered-rgb-flow-net","title":"PERF-Net: Pose Empowered RGB-Flow Net","date":"2020-09-28","arxiv_id":"2009.13087","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/spatiotemporal-contrastive-video","slug":"spatiotemporal-contrastive-video","title":"Spatiotemporal Contrastive Video Representation Learning","date":"2020-08-09","arxiv_id":"2008.03800","rows_on_this_dataset":6,"code_links":4,"syntology":null},{"paper":"/paper/self-supervised-video-representation-learning-3","slug":"self-supervised-video-representation-learning-3","title":"Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework","date":"2020-08-06","arxiv_id":"2008.02531","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":4,"samples_unverified":0,"pointer_only_for_licence":4,"official":{"repos":["BestJuly/Inter-intra-video-contrastive-learning"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/self-supervised-video-representation-learning-3#ran","syntology_url":"https://syntology.ai/paper/2008.02531","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.02531"}}}},{"paper":"/paper/late-temporal-modeling-in-3d-cnn","slug":"late-temporal-modeling-in-3d-cnn","title":"Late Temporal Modeling in 3D CNN Architectures with BERT for Action Recognition","date":"2020-08-03","arxiv_id":"2008.01232","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/bmbc-bilateral-motion-estimation-with","slug":"bmbc-bilateral-motion-estimation-with","title":"BMBC:Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation","date":"2020-07-17","arxiv_id":"2007.12622","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":4,"official":{"repos":["JunHeum/BMBC"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bmbc-bilateral-motion-estimation-with#ran","syntology_url":"https://syntology.ai/paper/2007.12622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.12622"}}}},{"paper":"/paper/self-supervised-multimodal-versatile-networks","slug":"self-supervised-multimodal-versatile-networks","title":"Self-Supervised MultiModal Versatile Networks","date":"2020-06-29","arxiv_id":"2006.16228","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/video-frame-interpolation-via-residue","slug":"video-frame-interpolation-via-residue","title":"Video Frame Interpolation via Residue Refinement","date":"2020-05-04","arxiv_id":null,"rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/audio-visual-instance-discrimination-with","slug":"audio-visual-instance-discrimination-with","title":"Audio-Visual Instance Discrimination with Cross-Modal Agreement","date":"2020-04-27","arxiv_id":"2004.12943","rows_on_this_dataset":5,"code_links":1,"syntology":null},{"paper":"/paper/omni-sourced-webly-supervised-learning-for","slug":"omni-sourced-webly-supervised-learning-for","title":"Omni-sourced Webly-supervised Learning for Video Recognition","date":"2020-03-29","arxiv_id":"2003.13042","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["open-mmlab/mmaction"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/omni-sourced-webly-supervised-learning-for#ran","syntology_url":"https://syntology.ai/paper/2003.13042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13042"}}}},{"paper":"/paper/temporally-coherent-embeddings-for-self","slug":"temporally-coherent-embeddings-for-self","title":"Temporally Coherent Embeddings for Self-Supervised Video Representation Learning","date":"2020-03-21","arxiv_id":"2004.02753","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["csiro-robotics/TCE"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/temporally-coherent-embeddings-for-self#ran","syntology_url":"https://syntology.ai/paper/2004.02753","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.02753"}}}},{"paper":"/paper/softmax-splatting-for-video-frame","slug":"softmax-splatting-for-video-frame","title":"Softmax Splatting for Video Frame Interpolation","date":"2020-03-11","arxiv_id":"2003.05534","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["sniklaus/softmax-splatting"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/softmax-splatting-for-video-frame#ran","syntology_url":"https://syntology.ai/paper/2003.05534","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.05534"}}}},{"paper":"/paper/rethinking-zero-shot-video-classification-end","slug":"rethinking-zero-shot-video-classification-end","title":"Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications","date":"2020-03-03","arxiv_id":"2003.01455","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["bbrattoli/ZeroShotVideoClassification"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/rethinking-zero-shot-video-classification-end#ran","syntology_url":"https://syntology.ai/paper/2003.01455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.01455"}}}},{"paper":"/paper/evolving-losses-for-unsupervised-video","slug":"evolving-losses-for-unsupervised-video","title":"Evolving Losses for Unsupervised Video Representation Learning","date":"2020-02-26","arxiv_id":"2002.12177","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-spatio-temporal-representations-with","slug":"learning-spatio-temporal-representations-with","title":"Learning spatio-temporal representations with temporal squeeze pooling","date":"2020-02-11","arxiv_id":"2002.04685","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/few-shot-action-recognition-via-improved","slug":"few-shot-action-recognition-via-improved","title":"Few-shot Action Recognition with Permutation-invariant Attention","date":"2020-01-12","arxiv_id":"2001.03905","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/video-cloze-procedure-for-self-supervised","slug":"video-cloze-procedure-for-self-supervised","title":"Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning","date":"2020-01-02","arxiv_id":"2001.00294","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-cloze-procedure-for-self-supervised#ran","syntology_url":"https://syntology.ai/paper/2001.00294","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.00294"}}}},{"paper":"/paper/lower-dimensional-kernels-for-video","slug":"lower-dimensional-kernels-for-video","title":"Lower Dimensional Kernels for Video Discriminators","date":"2019-12-18","arxiv_id":"1912.08860","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/hallucinet-ing-spatiotemporal-representations","slug":"hallucinet-ing-spatiotemporal-representations","title":"HalluciNet-ing Spatiotemporal Representations Using a 2D-CNN","date":"2019-12-10","arxiv_id":"1912.04430","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/self-supervised-learning-by-cross-modal-audio","slug":"self-supervised-learning-by-cross-modal-audio","title":"Self-Supervised Learning by Cross-Modal Audio-Video Clustering","date":"2019-11-28","arxiv_id":"1911.12667","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["HumamAlwassel/XDC"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/self-supervised-learning-by-cross-modal-audio#ran","syntology_url":"https://syntology.ai/paper/1911.12667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.12667"}}}},{"paper":"/paper/skip-clip-self-supervised-spatiotemporal","slug":"skip-clip-self-supervised-spatiotemporal","title":"Skip-Clip: Self-Supervised Spatiotemporal Representation Learning by Future Clip Order Ranking","date":"2019-10-28","arxiv_id":"1910.12770","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/markov-decision-process-for-video-generation","slug":"markov-decision-process-for-video-generation","title":"Markov Decision Process for Video Generation","date":"2019-09-26","arxiv_id":"1909.12400","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/mlgcn-multi-laplacian-graph-convolutional","slug":"mlgcn-multi-laplacian-graph-convolutional","title":"MLGCN: Multi-Laplacian Graph Convolutional Networks for Human Action Recognition","date":"2019-09-11","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/video-representation-learning-by-dense","slug":"video-representation-learning-by-dense","title":"Video Representation Learning by Dense Predictive Coding","date":"2019-09-10","arxiv_id":"1909.04656","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["TengdaHan/DPC"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-representation-learning-by-dense#ran","syntology_url":"https://syntology.ai/paper/1909.04656","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.04656"}}}},{"paper":"/paper/cooperative-cross-stream-network-for","slug":"cooperative-cross-stream-network-for","title":"Cooperative Cross-Stream Network for Discriminative Action Representation","date":"2019-08-27","arxiv_id":"1908.10136","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/i3d-lstm-a-new-model-for-human-action","slug":"i3d-lstm-a-new-model-for-human-action","title":"I3D-LSTM: A New Model for Human Action Recognition","date":"2019-08-09","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/stm-spatiotemporal-and-motion-encoding-for","slug":"stm-spatiotemporal-and-motion-encoding-for","title":"STM: SpatioTemporal and Motion Encoding for Action Recognition","date":"2019-08-07","arxiv_id":"1908.02486","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/two-stream-video-classification-with-cross","slug":"two-stream-video-classification-with-cross","title":"Two-Stream Video Classification with Cross-Modality Attention","date":"2019-08-01","arxiv_id":"1908.00497","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/i-know-the-relationships-zero-shot-action","slug":"i-know-the-relationships-zero-shot-action","title":"I Know the Relationships: Zero-Shot Action Recognition via Two-Stream Graph Convolutional Networks and Knowledge Graphs","date":"2019-07-17","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/r-stan-residual-spatial-temporal-attention","slug":"r-stan-residual-spatial-temporal-attention","title":"R-STAN: Residual Spatial-Temporal Attention Network for Action Recognition","date":"2019-06-19","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/contrastive-multiview-coding","slug":"contrastive-multiview-coding","title":"Contrastive Multiview Coding","date":"2019-06-13","arxiv_id":"1906.05849","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["HobbitLong/CMC"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/contrastive-multiview-coding#ran","syntology_url":"https://syntology.ai/paper/1906.05849","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.05849"}}}},{"paper":"/paper/learning-spatio-temporal-representation-with-3","slug":"learning-spatio-temporal-representation-with-3","title":"Learning Spatio-Temporal Representation with Local and Global Diffusion","date":"2019-06-13","arxiv_id":"1906.05571","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/unsupervised-video-interpolation-using-cycle","slug":"unsupervised-video-interpolation-using-cycle","title":"Unsupervised Video Interpolation Using Cycle Consistency","date":"2019-06-13","arxiv_id":"1906.05928","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/faster-recurrent-networks-for-video","slug":"faster-recurrent-networks-for-video","title":"FASTER Recurrent Networks for Efficient Video Classification","date":"2019-06-10","arxiv_id":"1906.04226","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/mars-motion-augmented-rgb-stream-for-action","slug":"mars-motion-augmented-rgb-stream-for-action","title":"MARS: Motion-Augmented RGB Stream for Action Recognition","date":"2019-06-01","arxiv_id":null,"rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/self-supervised-spatiotemporal-learning-via","slug":"self-supervised-spatiotemporal-learning-via","title":"Self-Supervised Spatiotemporal Learning via Video Clip Order Prediction","date":"2019-06-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/holistic-large-scale-video-understanding","slug":"holistic-large-scale-video-understanding","title":"Large Scale Holistic Video Understanding","date":"2019-04-25","arxiv_id":"1904.11451","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/self-supervised-spatio-temporal","slug":"self-supervised-spatio-temporal","title":"Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics","date":"2019-04-07","arxiv_id":"1904.03597","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/paying-more-attention-to-motion-attention","slug":"paying-more-attention-to-motion-attention","title":"Attention Distillation for Learning Video Representations","date":"2019-04-05","arxiv_id":"1904.03249","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/resource-efficient-3d-convolutional-neural","slug":"resource-efficient-3d-convolutional-neural","title":"Resource Efficient 3D Convolutional Neural Networks","date":"2019-04-04","arxiv_id":"1904.02422","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/dance-with-flow-two-in-one-stream-action","slug":"dance-with-flow-two-in-one-stream-action","title":"Dance with Flow: Two-in-One Stream Action Detection","date":"2019-04-01","arxiv_id":"1904.00696","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/depth-aware-video-frame-interpolation","slug":"depth-aware-video-frame-interpolation","title":"Depth-Aware Video Frame Interpolation","date":"2019-04-01","arxiv_id":"1904.00830","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["baowenbo/DAIN"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/depth-aware-video-frame-interpolation#ran","syntology_url":"https://syntology.ai/paper/1904.00830","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.00830"}}}},{"paper":"/paper/contextual-action-cues-from-camera-sensor-for","slug":"contextual-action-cues-from-camera-sensor-for","title":"Contextual Action Cues from Camera Sensor for Multi-Stream Action Recognition","date":"2019-03-20","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/distinit-learning-video-representations","slug":"distinit-learning-video-representations","title":"DistInit: Learning Video Representations Without a Single Labeled Video","date":"2019-01-26","arxiv_id":"1901.09244","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/dmc-net-generating-discriminative-motion-cues","slug":"dmc-net-generating-discriminative-motion-cues","title":"DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition","date":"2019-01-11","arxiv_id":"1901.03460","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/d3d-distilled-3d-networks-for-video-action","slug":"d3d-distilled-3d-networks-for-video-action","title":"D3D: Distilled 3D Networks for Video Action Recognition","date":"2018-12-19","arxiv_id":"1812.08249","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/self-supervised-spatiotemporal-feature","slug":"self-supervised-spatiotemporal-feature","title":"Self-Supervised Spatiotemporal Feature Learning via Video Rotation Prediction","date":"2018-11-28","arxiv_id":"1811.11387","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/self-supervised-video-representation-learning","slug":"self-supervised-video-representation-learning","title":"Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles","date":"2018-11-24","arxiv_id":"1811.09795","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/tganv2-efficient-training-of-large-models-for","slug":"tganv2-efficient-training-of-large-models-for","title":"Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN","date":"2018-11-22","arxiv_id":"1811.09245","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["pfnet-research/tgan2"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tganv2-efficient-training-of-large-models-for#ran","syntology_url":"https://syntology.ai/paper/1811.09245","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.09245"}}}},{"paper":"/paper/a2-nets-double-attention-networks","slug":"a2-nets-double-attention-networks","title":"$A^2$-Nets: Double Attention Networks","date":"2018-10-27","arxiv_id":"1810.11579","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/temporal-spatial-mapping-for-action","slug":"temporal-spatial-mapping-for-action","title":"Temporal-Spatial Mapping for Action Recognition","date":"2018-09-11","arxiv_id":"1809.03669","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multi-fiber-networks-for-video-recognition","slug":"multi-fiber-networks-for-video-recognition","title":"Multi-Fiber Networks for Video Recognition","date":"2018-07-30","arxiv_id":"1807.11195","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/cooperative-learning-of-audio-and-video","slug":"cooperative-learning-of-audio-and-video","title":"Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization","date":"2018-06-30","arxiv_id":"1807.00230","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-and-using-the-arrow-of-time","slug":"learning-and-using-the-arrow-of-time","title":"Learning and Using the Arrow of Time","date":"2018-06-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/potion-pose-motion-representation-for-action","slug":"potion-pose-motion-representation-for-action","title":"PoTion: Pose MoTion Representation for Action Recognition","date":"2018-06-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/end-to-end-learning-of-motion-representation","slug":"end-to-end-learning-of-motion-representation","title":"End-to-End Learning of Motion Representation for Video Understanding","date":"2018-04-02","arxiv_id":"1804.00413","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/end-to-end-learning-of-motion-representation#ran","syntology_url":"https://syntology.ai/paper/1804.00413","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.00413"}}}},{"paper":"/paper/towards-universal-representation-for-unseen","slug":"towards-universal-representation-for-unseen","title":"Towards Universal Representation for Unseen Action Recognition","date":"2018-03-22","arxiv_id":"1803.08460","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/rethinking-spatiotemporal-feature-learning","slug":"rethinking-spatiotemporal-feature-learning","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","date":"2017-12-13","arxiv_id":"1712.04851","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/a-closer-look-at-spatiotemporal-convolutions","slug":"a-closer-look-at-spatiotemporal-convolutions","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","date":"2017-11-30","arxiv_id":"1711.11248","rows_on_this_dataset":6,"code_links":24,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":4,"official":{"repos":["facebookresearch/R2Plus1D"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-closer-look-at-spatiotemporal-convolutions#ran","syntology_url":"https://syntology.ai/paper/1711.11248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.11248"}}}},{"paper":"/paper/optical-flow-guided-feature-a-fast-and-robust","slug":"optical-flow-guided-feature-a-fast-and-robust","title":"Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition","date":"2017-11-29","arxiv_id":"1711.11152","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-spatio-temporal-representation-with","slug":"learning-spatio-temporal-representation-with","title":"Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks","date":"2017-11-28","arxiv_id":"1711.10305","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/can-spatiotemporal-3d-cnns-retrace-the","slug":"can-spatiotemporal-3d-cnns-retrace-the","title":"Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?","date":"2017-11-27","arxiv_id":"1711.09577","rows_on_this_dataset":1,"code_links":26,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":7,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["kenshohara/3D-ResNets-PyTorch"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/can-spatiotemporal-3d-cnns-retrace-the#ran","syntology_url":"https://syntology.ai/paper/1711.09577","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.09577"}}}},{"paper":"/paper/appearance-and-relation-networks-for-video","slug":"appearance-and-relation-networks-for-video","title":"Appearance-and-Relation Networks for Video Classification","date":"2017-11-24","arxiv_id":"1711.09125","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/convnet-architecture-search-for","slug":"convnet-architecture-search-for","title":"ConvNet Architecture Search for Spatiotemporal Feature Learning","date":"2017-08-16","arxiv_id":"1708.05038","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mocogan-decomposing-motion-and-content-for","slug":"mocogan-decomposing-motion-and-content-for","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","date":"2017-07-17","arxiv_id":"1707.04993","rows_on_this_dataset":2,"code_links":5,"syntology":null},{"paper":"/paper/zero-shot-action-recognition-with-error","slug":"zero-shot-action-recognition-with-error","title":"Zero-Shot Action Recognition With Error-Correcting Output Codes","date":"2017-07-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/alternative-semantic-representations-for-zero","slug":"alternative-semantic-representations-for-zero","title":"Alternative Semantic Representations for Zero-Shot Human Action Recognition","date":"2017-06-28","arxiv_id":"1706.09317","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/quo-vadis-action-recognition-a-new-model-and","slug":"quo-vadis-action-recognition-a-new-model-and","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","date":"2017-05-22","arxiv_id":"1705.07750","rows_on_this_dataset":7,"code_links":34,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":28,"samples_ran":16,"samples_constructed":7,"samples_ran_checked":10,"samples_ran_instrument_failed":6,"samples_unverified":12,"pointer_only_for_licence":7,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/quo-vadis-action-recognition-a-new-model-and#ran","syntology_url":"https://syntology.ai/paper/1705.07750","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.07750"}}}},{"paper":"/paper/hidden-two-stream-convolutional-networks-for","slug":"hidden-two-stream-convolutional-networks-for","title":"Hidden Two-Stream Convolutional Networks for Action Recognition","date":"2017-04-02","arxiv_id":"1704.00389","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/ts-lstm-and-temporal-inception-exploiting","slug":"ts-lstm-and-temporal-inception-exploiting","title":"TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity Recognition","date":"2017-03-30","arxiv_id":"1703.10667","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/actionflownet-learning-motion-representation","slug":"actionflownet-learning-motion-representation","title":"ActionFlowNet: Learning Motion Representation for Action Recognition","date":"2016-12-09","arxiv_id":"1612.03052","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multi-task-zero-shot-action-recognition-with","slug":"multi-task-zero-shot-action-recognition-with","title":"Multi-Task Zero-Shot Action Recognition with Prioritised Data Augmentation","date":"2016-11-26","arxiv_id":"1611.08663","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/self-supervised-video-representation-learning-1","slug":"self-supervised-video-representation-learning-1","title":"Self-Supervised Video Representation Learning With Odd-One-Out Networks","date":"2016-11-21","arxiv_id":"1611.06646","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/temporal-generative-adversarial-nets-with","slug":"temporal-generative-adversarial-nets-with","title":"Temporal Generative Adversarial Nets with Singular Value Clipping","date":"2016-11-21","arxiv_id":"1611.06624","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/temporal-generative-adversarial-nets-with#ran","syntology_url":"https://syntology.ai/paper/1611.06624","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.06624"}}}},{"paper":"/paper/spatiotemporal-residual-networks-for-video","slug":"spatiotemporal-residual-networks-for-video","title":"Spatiotemporal Residual Networks for Video Action Recognition","date":"2016-11-07","arxiv_id":"1611.02155","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-region-two-stream-r-cnn-for-action","slug":"multi-region-two-stream-r-cnn-for-action","title":"Multi-region two-stream R-CNN for action detection","date":"2016-09-17","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/generating-videos-with-scene-dynamics","slug":"generating-videos-with-scene-dynamics","title":"Generating Videos with Scene Dynamics","date":"2016-09-08","arxiv_id":"1609.02612","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/temporal-segment-networks-towards-good","slug":"temporal-segment-networks-towards-good","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","date":"2016-08-02","arxiv_id":"1608.00859","rows_on_this_dataset":1,"code_links":22,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":24,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":14,"pointer_only_for_licence":3,"official":{"repos":["yjxiong/caffe","yjxiong/temporal-segment-networks"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/temporal-segment-networks-towards-good#ran","syntology_url":"https://syntology.ai/paper/1608.00859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1608.00859"}}}},{"paper":"/paper/dynamic-image-networks-for-action-recognition","slug":"dynamic-image-networks-for-action-recognition","title":"Dynamic Image Networks for Action Recognition","date":"2016-06-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/real-time-action-recognition-with-enhanced","slug":"real-time-action-recognition-with-enhanced","title":"Real-time Action Recognition with Enhanced Motion Vector CNNs","date":"2016-04-26","arxiv_id":"1604.07669","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/convolutional-two-stream-network-fusion-for","slug":"convolutional-two-stream-network-fusion-for","title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","date":"2016-04-22","arxiv_id":"1604.06573","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/long-term-temporal-convolutions-for-action","slug":"long-term-temporal-convolutions-for-action","title":"Long-term Temporal Convolutions for Action Recognition","date":"2016-04-15","arxiv_id":"1604.04494","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/shuffle-and-learn-unsupervised-learning-using","slug":"shuffle-and-learn-unsupervised-learning-using","title":"Shuffle and Learn: Unsupervised Learning using Temporal Order Verification","date":"2016-03-28","arxiv_id":"1603.08561","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/objects2action-classifying-and-localizing","slug":"objects2action-classifying-and-localizing","title":"Objects2action: Classifying and localizing actions without any video example","date":"2015-10-23","arxiv_id":"1510.06939","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/towards-good-practices-for-very-deep-two","slug":"towards-good-practices-for-very-deep-two","title":"Towards Good Practices for Very Deep Two-Stream ConvNets","date":"2015-07-08","arxiv_id":"1507.02159","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/an-embarrassingly-simple-approach-to-zero","slug":"an-embarrassingly-simple-approach-to-zero","title":"An embarrassingly simple approach to zero-shot learning","date":"2015-07-06","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/action-recognition-with-trajectory-pooled","slug":"action-recognition-with-trajectory-pooled","title":"Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors","date":"2015-05-19","arxiv_id":"1505.04868","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/beyond-short-snippets-deep-networks-for-video","slug":"beyond-short-snippets-deep-networks-for-video","title":"Beyond Short Snippets: Deep Networks for Video Classification","date":"2015-03-31","arxiv_id":"1503.08909","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/beyond-short-snippets-deep-networks-for-video#ran","syntology_url":"https://syntology.ai/paper/1503.08909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1503.08909"}}}},{"paper":"/paper/semantic-embedding-space-for-zero-shot-action","slug":"semantic-embedding-space-for-zero-shot-action","title":"Semantic Embedding Space for Zero-Shot Action Recognition","date":"2015-02-05","arxiv_id":"1502.01540","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-spatiotemporal-features-with-3d","slug":"learning-spatiotemporal-features-with-3d","title":"Learning Spatiotemporal Features with 3D Convolutional Networks","date":"2014-12-02","arxiv_id":"1412.0767","rows_on_this_dataset":1,"code_links":29,"syntology":null},{"paper":"/paper/evaluation-of-output-embeddings-for-fine","slug":"evaluation-of-output-embeddings-for-fine","title":"Evaluation of Output Embeddings for Fine-Grained Image Classification","date":"2014-09-30","arxiv_id":"1409.8403","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/large-scale-video-classification-with-1","slug":"large-scale-video-classification-with-1","title":"Large-Scale Video Classification with Convolutional Neural Networks","date":"2014-06-23","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/two-stream-convolutional-networks-for-action","slug":"two-stream-convolutional-networks-for-action","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","date":"2014-06-09","arxiv_id":"1406.2199","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["feichtenhofer/twostreamfusion"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/two-stream-convolutional-networks-for-action#ran","syntology_url":"https://syntology.ai/paper/1406.2199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1406.2199"}}}},{"paper":"/paper/ucf101-a-dataset-of-101-human-actions-classes","slug":"ucf101-a-dataset-of-101-human-actions-classes","title":"UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild","date":"2012-12-03","arxiv_id":"1212.0402","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ucf101-a-dataset-of-101-human-actions-classes#ran","syntology_url":"https://syntology.ai/paper/1212.0402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1212.0402"}}}}],"papers_where_code_ran":75,"papers_where_code_ran_first_page":"/dataset/ucf101/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"archive","page":2,"of":3,"url":"/dataset/ucf101/papers/2","json":"/dataset/ucf101/papers/2.json","rows":100},{"order":"archive","page":3,"of":3,"url":"/dataset/ucf101/papers/3","json":"/dataset/ucf101/papers/3.json","rows":28},{"order":"ran","page":1,"of":1,"url":"/dataset/ucf101/papers/ran/1","json":"/dataset/ucf101/papers/ran/1.json","rows":75}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":83,"samples_harvested":632,"samples_ran":452,"samples_constructed":43,"samples_ran_checked":284,"samples_ran_instrument_failed":168,"samples_unverified":180,"pointer_only_for_licence":196,"papers_with_no_sample_that_ran":8,"papers_with_a_sample_that_ran":75,"papers_with_a_run_with_no_instrument_failure":65,"papers_where_every_run_was_an_instrument_failure":10,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"eec63d7a032467589648d57782d7d64d728172bd486d7051bc17c4c7468e751d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}