{"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/kinetics-600","name":"Kinetics-600","full_name":null,"description_markdown":"The **Kinetics-600** is a large-scale action recognition dataset which consists of around 480K videos from 600 action categories. The 480K videos are divided into 390K, 30K, 60K for training, validation and test sets, respectively. Each video in the dataset is a 10-second clip of action moment annotated from raw YouTube video. It is an extensions of the Kinetics-400 dataset.\r\n\r\nSource: [Learning to Localize Actions from Moments](https://arxiv.org/abs/2008.13705)\r\nImage Source: [https://towardsdatascience.com/downloading-the-kinetics-dataset-for-human-action-recognition-in-deep-learning-500c3d50f776](https://towardsdatascience.com/downloading-the-kinetics-dataset-for-human-action-recognition-in-deep-learning-500c3d50f776)","description_withheld":null,"homepage":"https://deepmind.com/research/open-source/kinetics","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/a-short-note-about-kinetics-600","title":"A Short Note about Kinetics-600","first_author":"Joao Carreira","url":null},"license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"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":"Video Prediction","url":"/task/video-prediction","datasets_with_task":"/datasets/task/video-prediction"},{"name":"Video Generation","url":"/task/video-generation","datasets_with_task":"/datasets/task/video-generation"},{"name":"Self-Supervised Action Recognition","url":"/task/self-supervised-action-recognition","datasets_with_task":"/datasets/task/self-supervised-action-recognition"}],"languages":[],"variants":["Kinetics-600 12 frames, 64x64","Kinetics-600 48 frames, 64x64","Kinetics-600 12 frames, 128x128","Kinetics-600"],"data_loaders":[{"repo":"https://github.com/voxel51/fiftyone","url":"https://docs.voxel51.com/user_guide/dataset_zoo/datasets.html#kinetics-600","frameworks":["tf","pytorch"]},{"repo":"https://github.com/open-mmlab/mmaction2","url":"https://github.com/open-mmlab/mmaction2/blob/master/tools/data/kinetics/README.md","frameworks":["pytorch"]}],"num_papers_in_archive":148,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/action-classification-on-kinetics-600","task":"Action Classification","dataset_variant":"Kinetics-600","rows":65,"metrics":["Top-1 Accuracy","Top-5 Accuracy","GFLOPs"],"first_row_in_archive_order":{"model":"InternVideo2-6B","paper":"/paper/internvideo2-scaling-video-foundation-models","metrics":{"Top-1 Accuracy":"91.9"},"code_links":[{"title":"opengvlab/internvideo","url":"https://github.com/opengvlab/internvideo"},{"title":"opengvlab/internvideo2","url":"https://github.com/opengvlab/internvideo2"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/self-supervised-action-recognition-on","task":"Self-Supervised Action Recognition","dataset_variant":"Kinetics-600","rows":5,"metrics":["Top-1 Accuracy"],"first_row_in_archive_order":{"model":"CVRL (R3D-152 2x)","paper":"/paper/spatiotemporal-contrastive-video","metrics":{"Top-1 Accuracy":"72.9"},"code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/official/projects/video_ssl"},{"title":"ed-fish/spatio-temporal-contrastive-film","url":"https://github.com/ed-fish/spatio-temporal-contrastive-film"},{"title":"ed-fish/spatio-temporal-contrastive-video","url":"https://github.com/ed-fish/spatio-temporal-contrastive-video"},{"title":"applecrumble123/CVLR_pytorch","url":"https://github.com/applecrumble123/CVLR_pytorch"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/action-recognition-in-videos-on-kinetics-600","task":"Action Recognition In Videos","dataset_variant":"Kinetics-600","rows":1,"metrics":["Top-1 Accuracy","Top-5 Accuracy"],"first_row_in_archive_order":{"model":"Florence","paper":"/paper/florence-a-new-foundation-model-for-computer","metrics":{"Top-1 Accuracy":"87.8","Top-5 Accuracy":"97.8"},"code_links":[{"title":"microsoft/unicl","url":"https://github.com/microsoft/unicl"},{"title":"MindCode-4/code-3","url":"https://github.com/MindCode-4/code-3/tree/main/florence2"}]},"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":1,"rows_per_page":100,"shown":35,"of":35,"counts":{"papers_with_a_benchmark_row":35,"with_a_code_link":31,"where_syntology_ran_a_sample":18,"not_listed_spam_title":0,"listed":35,"listed_where_code_ran":18,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":16,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":16,"listed_every_run_a_failure_of_syntologys_instrument":2,"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/internvideo2-scaling-video-foundation-models","slug":"internvideo2-scaling-video-foundation-models","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","date":"2024-03-22","arxiv_id":"2403.15377","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/hiera-a-hierarchical-vision-transformer","slug":"hiera-a-hierarchical-vision-transformer","title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","date":"2023-06-01","arxiv_id":"2306.00989","rows_on_this_dataset":1,"code_links":4,"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":["facebookresearch/hiera"],"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/hiera-a-hierarchical-vision-transformer#ran","syntology_url":"https://syntology.ai/paper/2306.00989","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00989"}}}},{"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/unmasked-teacher-towards-training-efficient","slug":"unmasked-teacher-towards-training-efficient","title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","date":"2023-03-28","arxiv_id":"2303.16058","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":7,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["opengvlab/unmasked_teacher"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unmasked-teacher-towards-training-efficient#ran","syntology_url":"https://syntology.ai/paper/2303.16058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16058"}}}},{"paper":"/paper/mplug-2-a-modularized-multi-modal-foundation","slug":"mplug-2-a-modularized-multi-modal-foundation","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","date":"2023-02-01","arxiv_id":"2302.00402","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":17,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":9,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["alibaba/AliceMind"],"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/mplug-2-a-modularized-multi-modal-foundation#ran","syntology_url":"https://syntology.ai/paper/2302.00402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.00402"}}}},{"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/rethinking-video-vits-sparse-video-tubes-for","slug":"rethinking-video-vits-sparse-video-tubes-for","title":"Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning","date":"2022-12-06","arxiv_id":"2212.03229","rows_on_this_dataset":3,"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":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/rethinking-video-vits-sparse-video-tubes-for#ran","syntology_url":"https://syntology.ai/paper/2212.03229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03229"}}}},{"paper":"/paper/eva-exploring-the-limits-of-masked-visual","slug":"eva-exploring-the-limits-of-masked-visual","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","date":"2022-11-14","arxiv_id":"2211.07636","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["baaivision/eva","rwightman/pytorch-image-models"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/eva-exploring-the-limits-of-masked-visual#ran","syntology_url":"https://syntology.ai/paper/2211.07636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.07636"}}}},{"paper":"/paper/uniformerv2-spatiotemporal-learning-by-arming","slug":"uniformerv2-spatiotemporal-learning-by-arming","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","date":"2022-09-22","arxiv_id":null,"rows_on_this_dataset":1,"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/coca-contrastive-captioners-are-image-text","slug":"coca-contrastive-captioners-are-image-text","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","date":"2022-05-04","arxiv_id":"2205.01917","rows_on_this_dataset":2,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":10,"samples_constructed":5,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":7,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/coca-contrastive-captioners-are-image-text#ran","syntology_url":"https://syntology.ai/paper/2205.01917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01917"}}}},{"paper":"/paper/multiview-transformers-for-video-recognition","slug":"multiview-transformers-for-video-recognition","title":"Multiview Transformers for Video Recognition","date":"2022-01-12","arxiv_id":"2201.04288","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/merlot-reserve-neural-script-knowledge","slug":"merlot-reserve-neural-script-knowledge","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","date":"2022-01-07","arxiv_id":"2201.02639","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/masked-feature-prediction-for-self-supervised","slug":"masked-feature-prediction-for-self-supervised","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","date":"2021-12-16","arxiv_id":"2112.09133","rows_on_this_dataset":1,"code_links":6,"syntology":null},{"paper":"/paper/co-training-transformer-with-videos-and","slug":"co-training-transformer-with-videos-and","title":"Co-training Transformer with Videos and Images Improves Action Recognition","date":"2021-12-14","arxiv_id":"2112.07175","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/improved-multiscale-vision-transformers-for","slug":"improved-multiscale-vision-transformers-for","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","date":"2021-12-02","arxiv_id":"2112.01526","rows_on_this_dataset":4,"code_links":9,"syntology":null},{"paper":"/paper/florence-a-new-foundation-model-for-computer","slug":"florence-a-new-foundation-model-for-computer","title":"Florence: A New Foundation Model for Computer Vision","date":"2021-11-22","arxiv_id":"2111.11432","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/uniformer-unified-transformer-for-efficient","slug":"uniformer-unified-transformer-for-efficient","title":"UniFormer: Unified Transformer for Efficient Spatial-Temporal Representation Learning","date":"2021-09-29","arxiv_id":null,"rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/revisiting-3d-resnets-for-video-recognition","slug":"revisiting-3d-resnets-for-video-recognition","title":"Revisiting 3D ResNets for Video Recognition","date":"2021-09-03","arxiv_id":"2109.01696","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/video-swin-transformer","slug":"video-swin-transformer","title":"Video Swin Transformer","date":"2021-06-24","arxiv_id":"2106.13230","rows_on_this_dataset":2,"code_links":15,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":32,"samples_ran":19,"samples_constructed":0,"samples_ran_checked":14,"samples_ran_instrument_failed":5,"samples_unverified":13,"pointer_only_for_licence":7,"official":{"repos":["SwinTransformer/Video-Swin-Transformer"],"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":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-swin-transformer#ran","syntology_url":"https://syntology.ai/paper/2106.13230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13230"}}}},{"paper":"/paper/tokenlearner-what-can-8-learned-tokens-do-for","slug":"tokenlearner-what-can-8-learned-tokens-do-for","title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?","date":"2021-06-21","arxiv_id":"2106.11297","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":1,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["google-research/scenic"],"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/tokenlearner-what-can-8-learned-tokens-do-for#ran","syntology_url":"https://syntology.ai/paper/2106.11297","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11297"}}}},{"paper":"/paper/space-time-mixing-attention-for-video","slug":"space-time-mixing-attention-for-video","title":"Space-time Mixing Attention for Video Transformer","date":"2021-06-10","arxiv_id":"2106.05968","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":0,"official":{"repos":["1adrianb/video-transformers"],"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/space-time-mixing-attention-for-video#ran","syntology_url":"https://syntology.ai/paper/2106.05968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05968"}}}},{"paper":"/paper/multiscale-vision-transformers","slug":"multiscale-vision-transformers","title":"Multiscale Vision Transformers","date":"2021-04-22","arxiv_id":"2104.11227","rows_on_this_dataset":3,"code_links":8,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":26,"samples_ran":13,"samples_constructed":10,"samples_ran_checked":11,"samples_ran_instrument_failed":2,"samples_unverified":13,"pointer_only_for_licence":5,"official":{"repos":["facebookresearch/SlowFast"],"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/multiscale-vision-transformers#ran","syntology_url":"https://syntology.ai/paper/2104.11227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.11227"}}}},{"paper":"/paper/vatt-transformers-for-multimodal-self","slug":"vatt-transformers-for-multimodal-self","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","date":"2021-04-22","arxiv_id":"2104.11178","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":5,"samples_constructed":4,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":8,"official":{"repos":["google-research/google-research"],"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/vatt-transformers-for-multimodal-self#ran","syntology_url":"https://syntology.ai/paper/2104.11178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.11178"}}}},{"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":1,"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/2103-15691","slug":"2103-15691","title":"ViViT: A Video Vision Transformer","date":"2021-03-29","arxiv_id":"2103.15691","rows_on_this_dataset":3,"code_links":10,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":14,"samples_constructed":10,"samples_ran_checked":13,"samples_ran_instrument_failed":1,"samples_unverified":7,"pointer_only_for_licence":1,"official":{"repos":["google-research/scenic"],"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/2103-15691#ran","syntology_url":"https://syntology.ai/paper/2103.15691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.15691"}}}},{"paper":"/paper/movinets-mobile-video-networks-for-efficient","slug":"movinets-mobile-video-networks-for-efficient","title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","date":"2021-03-21","arxiv_id":"2103.11511","rows_on_this_dataset":8,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":9,"samples_constructed":6,"samples_ran_checked":8,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["tensorflow/models"],"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/movinets-mobile-video-networks-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2103.11511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.11511"}}}},{"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":3,"code_links":4,"syntology":null},{"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":1,"code_links":1,"syntology":null},{"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/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":2,"code_links":1,"syntology":null},{"paper":"/paper/slowfast-networks-for-video-recognition","slug":"slowfast-networks-for-video-recognition","title":"SlowFast Networks for Video Recognition","date":"2018-12-10","arxiv_id":"1812.03982","rows_on_this_dataset":5,"code_links":15,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["facebookresearch/SlowFast"],"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/slowfast-networks-for-video-recognition#ran","syntology_url":"https://syntology.ai/paper/1812.03982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.03982"}}}},{"paper":"/paper/a-short-note-about-kinetics-600","slug":"a-short-note-about-kinetics-600","title":"A Short Note about Kinetics-600","date":"2018-08-03","arxiv_id":"1808.01340","rows_on_this_dataset":1,"code_links":1,"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":3,"code_links":2,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/internvideo2-scaling-video-foundation-models","slug":"internvideo2-scaling-video-foundation-models","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","date":"2024-03-22","arxiv_id":"2403.15377","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/hiera-a-hierarchical-vision-transformer","slug":"hiera-a-hierarchical-vision-transformer","title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","date":"2023-06-01","arxiv_id":"2306.00989","rows_on_this_dataset":1,"code_links":4,"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":["facebookresearch/hiera"],"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/hiera-a-hierarchical-vision-transformer#ran","syntology_url":"https://syntology.ai/paper/2306.00989","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00989"}}}},{"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/unmasked-teacher-towards-training-efficient","slug":"unmasked-teacher-towards-training-efficient","title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","date":"2023-03-28","arxiv_id":"2303.16058","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":7,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["opengvlab/unmasked_teacher"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unmasked-teacher-towards-training-efficient#ran","syntology_url":"https://syntology.ai/paper/2303.16058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16058"}}}},{"paper":"/paper/mplug-2-a-modularized-multi-modal-foundation","slug":"mplug-2-a-modularized-multi-modal-foundation","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","date":"2023-02-01","arxiv_id":"2302.00402","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":17,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":9,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["alibaba/AliceMind"],"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/mplug-2-a-modularized-multi-modal-foundation#ran","syntology_url":"https://syntology.ai/paper/2302.00402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.00402"}}}},{"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/rethinking-video-vits-sparse-video-tubes-for","slug":"rethinking-video-vits-sparse-video-tubes-for","title":"Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning","date":"2022-12-06","arxiv_id":"2212.03229","rows_on_this_dataset":3,"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":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/rethinking-video-vits-sparse-video-tubes-for#ran","syntology_url":"https://syntology.ai/paper/2212.03229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03229"}}}},{"paper":"/paper/eva-exploring-the-limits-of-masked-visual","slug":"eva-exploring-the-limits-of-masked-visual","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","date":"2022-11-14","arxiv_id":"2211.07636","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["baaivision/eva","rwightman/pytorch-image-models"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/eva-exploring-the-limits-of-masked-visual#ran","syntology_url":"https://syntology.ai/paper/2211.07636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.07636"}}}},{"paper":"/paper/uniformerv2-spatiotemporal-learning-by-arming","slug":"uniformerv2-spatiotemporal-learning-by-arming","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","date":"2022-09-22","arxiv_id":null,"rows_on_this_dataset":1,"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/coca-contrastive-captioners-are-image-text","slug":"coca-contrastive-captioners-are-image-text","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","date":"2022-05-04","arxiv_id":"2205.01917","rows_on_this_dataset":2,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":10,"samples_constructed":5,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":7,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/coca-contrastive-captioners-are-image-text#ran","syntology_url":"https://syntology.ai/paper/2205.01917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01917"}}}},{"paper":"/paper/multiview-transformers-for-video-recognition","slug":"multiview-transformers-for-video-recognition","title":"Multiview Transformers for Video Recognition","date":"2022-01-12","arxiv_id":"2201.04288","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/merlot-reserve-neural-script-knowledge","slug":"merlot-reserve-neural-script-knowledge","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","date":"2022-01-07","arxiv_id":"2201.02639","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/masked-feature-prediction-for-self-supervised","slug":"masked-feature-prediction-for-self-supervised","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","date":"2021-12-16","arxiv_id":"2112.09133","rows_on_this_dataset":1,"code_links":6,"syntology":null},{"paper":"/paper/co-training-transformer-with-videos-and","slug":"co-training-transformer-with-videos-and","title":"Co-training Transformer with Videos and Images Improves Action Recognition","date":"2021-12-14","arxiv_id":"2112.07175","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/improved-multiscale-vision-transformers-for","slug":"improved-multiscale-vision-transformers-for","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","date":"2021-12-02","arxiv_id":"2112.01526","rows_on_this_dataset":4,"code_links":9,"syntology":null},{"paper":"/paper/florence-a-new-foundation-model-for-computer","slug":"florence-a-new-foundation-model-for-computer","title":"Florence: A New Foundation Model for Computer Vision","date":"2021-11-22","arxiv_id":"2111.11432","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/uniformer-unified-transformer-for-efficient","slug":"uniformer-unified-transformer-for-efficient","title":"UniFormer: Unified Transformer for Efficient Spatial-Temporal Representation Learning","date":"2021-09-29","arxiv_id":null,"rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/revisiting-3d-resnets-for-video-recognition","slug":"revisiting-3d-resnets-for-video-recognition","title":"Revisiting 3D ResNets for Video Recognition","date":"2021-09-03","arxiv_id":"2109.01696","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/video-swin-transformer","slug":"video-swin-transformer","title":"Video Swin Transformer","date":"2021-06-24","arxiv_id":"2106.13230","rows_on_this_dataset":2,"code_links":15,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":32,"samples_ran":19,"samples_constructed":0,"samples_ran_checked":14,"samples_ran_instrument_failed":5,"samples_unverified":13,"pointer_only_for_licence":7,"official":{"repos":["SwinTransformer/Video-Swin-Transformer"],"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":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-swin-transformer#ran","syntology_url":"https://syntology.ai/paper/2106.13230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13230"}}}},{"paper":"/paper/tokenlearner-what-can-8-learned-tokens-do-for","slug":"tokenlearner-what-can-8-learned-tokens-do-for","title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?","date":"2021-06-21","arxiv_id":"2106.11297","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":1,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["google-research/scenic"],"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/tokenlearner-what-can-8-learned-tokens-do-for#ran","syntology_url":"https://syntology.ai/paper/2106.11297","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11297"}}}},{"paper":"/paper/space-time-mixing-attention-for-video","slug":"space-time-mixing-attention-for-video","title":"Space-time Mixing Attention for Video Transformer","date":"2021-06-10","arxiv_id":"2106.05968","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":0,"official":{"repos":["1adrianb/video-transformers"],"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/space-time-mixing-attention-for-video#ran","syntology_url":"https://syntology.ai/paper/2106.05968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05968"}}}},{"paper":"/paper/multiscale-vision-transformers","slug":"multiscale-vision-transformers","title":"Multiscale Vision Transformers","date":"2021-04-22","arxiv_id":"2104.11227","rows_on_this_dataset":3,"code_links":8,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":26,"samples_ran":13,"samples_constructed":10,"samples_ran_checked":11,"samples_ran_instrument_failed":2,"samples_unverified":13,"pointer_only_for_licence":5,"official":{"repos":["facebookresearch/SlowFast"],"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/multiscale-vision-transformers#ran","syntology_url":"https://syntology.ai/paper/2104.11227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.11227"}}}},{"paper":"/paper/vatt-transformers-for-multimodal-self","slug":"vatt-transformers-for-multimodal-self","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","date":"2021-04-22","arxiv_id":"2104.11178","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":5,"samples_constructed":4,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":8,"official":{"repos":["google-research/google-research"],"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/vatt-transformers-for-multimodal-self#ran","syntology_url":"https://syntology.ai/paper/2104.11178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.11178"}}}},{"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":1,"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/2103-15691","slug":"2103-15691","title":"ViViT: A Video Vision Transformer","date":"2021-03-29","arxiv_id":"2103.15691","rows_on_this_dataset":3,"code_links":10,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":14,"samples_constructed":10,"samples_ran_checked":13,"samples_ran_instrument_failed":1,"samples_unverified":7,"pointer_only_for_licence":1,"official":{"repos":["google-research/scenic"],"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/2103-15691#ran","syntology_url":"https://syntology.ai/paper/2103.15691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.15691"}}}},{"paper":"/paper/movinets-mobile-video-networks-for-efficient","slug":"movinets-mobile-video-networks-for-efficient","title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","date":"2021-03-21","arxiv_id":"2103.11511","rows_on_this_dataset":8,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":9,"samples_constructed":6,"samples_ran_checked":8,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["tensorflow/models"],"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/movinets-mobile-video-networks-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2103.11511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.11511"}}}},{"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":3,"code_links":4,"syntology":null},{"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":1,"code_links":1,"syntology":null},{"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/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":2,"code_links":1,"syntology":null},{"paper":"/paper/slowfast-networks-for-video-recognition","slug":"slowfast-networks-for-video-recognition","title":"SlowFast Networks for Video Recognition","date":"2018-12-10","arxiv_id":"1812.03982","rows_on_this_dataset":5,"code_links":15,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["facebookresearch/SlowFast"],"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/slowfast-networks-for-video-recognition#ran","syntology_url":"https://syntology.ai/paper/1812.03982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.03982"}}}},{"paper":"/paper/a-short-note-about-kinetics-600","slug":"a-short-note-about-kinetics-600","title":"A Short Note about Kinetics-600","date":"2018-08-03","arxiv_id":"1808.01340","rows_on_this_dataset":1,"code_links":1,"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":3,"code_links":2,"syntology":null}],"papers_where_code_ran":18,"papers_where_code_ran_first_page":"/dataset/kinetics-600/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":"ran","page":1,"of":1,"url":"/dataset/kinetics-600/papers/ran/1","json":"/dataset/kinetics-600/papers/ran/1.json","rows":18}],"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":18,"samples_harvested":190,"samples_ran":132,"samples_constructed":41,"samples_ran_checked":107,"samples_ran_instrument_failed":25,"samples_unverified":58,"pointer_only_for_licence":33,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":18,"papers_with_a_run_with_no_instrument_failure":16,"papers_where_every_run_was_an_instrument_failure":2,"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":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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":[{"leaderboard":"/sota/action-classification-on-kinetics-600","since_archive":"/sota/action-classification-on-kinetics-600#since-judged","papers_judged":1,"placed":0}]},"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":"45389f27b5c8418f874f27c30a56dddec7e397541de4d3601b1d4cb2a540ffb5","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}