{"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/msr-vtt","name":"MSR-VTT","full_name":null,"description_markdown":"**MSR-VTT** (Microsoft Research Video to Text) is a large-scale dataset for the open domain video captioning, which consists of 10,000 video clips from 20 categories, and each video clip is annotated with 20 English sentences by Amazon Mechanical Turks. There are about 29,000 unique words in all captions. The standard splits uses 6,513 clips for training, 497 clips for validation, and 2,990 clips for testing.\r\n\r\nSource: [Learning to Discretely Compose Reasoning Module Networksfor Video Captioning](https://arxiv.org/abs/2007.09049)","description_withheld":null,"homepage":"https://www.microsoft.com/en-us/research/publication/msr-vtt-a-large-video-description-dataset-for-bridging-video-and-language/","introduced_date":"2016-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/msr-vtt-a-large-video-description-dataset-for","title":"MSR-VTT: A Large Video Description Dataset for Bridging Video and Language","first_author":"Jun Xu","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Video Question Answering","url":"/task/video-question-answering","datasets_with_task":"/datasets/task/video-question-answering"},{"name":"Video Retrieval","url":"/task/video-retrieval","datasets_with_task":"/datasets/task/video-retrieval"},{"name":"Video Captioning","url":"/task/video-captioning","datasets_with_task":"/datasets/task/video-captioning"},{"name":"Video Generation","url":"/task/video-generation","datasets_with_task":"/datasets/task/video-generation"},{"name":"Zero-Shot Video Retrieval","url":"/task/zero-shot-video-retrieval","datasets_with_task":"/datasets/task/zero-shot-video-retrieval"},{"name":"Text-to-Video Generation","url":"/task/text-to-video-generation","datasets_with_task":"/datasets/task/text-to-video-generation"},{"name":"Text to Video Retrieval","url":"/task/text-to-video-retrieval","datasets_with_task":"/datasets/task/text-to-video-retrieval"},{"name":"Zero-Shot Video-Audio Retrieval","url":"/task/zero-shot-video-audio-retrieval","datasets_with_task":"/datasets/task/zero-shot-video-audio-retrieval"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MSR-VTT","MSR-VTT-1kA","MSRVTT"],"data_loaders":[{"repo":"https://github.com/Ishihara-Masabumi/Image_Generation_by_DiT","url":"https://github.com/Ishihara-Masabumi/Image_Generation_by_DiT","frameworks":["tf","pytorch"]}],"num_papers_in_archive":640,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/video-retrieval-on-msr-vtt-1ka","task":"Video Retrieval","dataset_variant":"MSR-VTT-1kA","rows":63,"metrics":["text-to-video R@1","text-to-video R@5","text-to-video R@10","text-to-video Median Rank","text-to-video Mean Rank","video-to-text R@1","video-to-text R@5","video-to-text R@10","video-to-text Median Rank","video-to-text Mean Rank"],"first_row_in_archive_order":{"model":"HunYuan_tvr (huge)","paper":"/paper/hunyuan-tvr-for-text-video-retrivial","metrics":{"text-to-video Mean Rank":"9.3 ","text-to-video Median Rank":"1.0","text-to-video R@1":"62.9","text-to-video R@10":"90.8","text-to-video R@5":"84.5","video-to-text Mean Rank":"5.5","video-to-text Median Rank":"1.0","video-to-text R@1":"64.8","video-to-text R@10":"91.1","video-to-text R@5":"84.9"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/zero-shot-video-retrieval-on-msr-vtt","task":"Zero-Shot Video Retrieval","dataset_variant":"MSR-VTT","rows":41,"metrics":["text-to-video R@1","text-to-video R@5","text-to-video R@10","text-to-video Median Rank","text-to-video Mean Rank","video-to-text R@1","video-to-text R@5","video-to-text R@10","video-to-text Median Rank"],"first_row_in_archive_order":{"model":"InternVideo2-6B","paper":"/paper/internvideo2-scaling-video-foundation-models","metrics":{"text-to-video R@1":"55.9","text-to-video R@10":"85.1","text-to-video R@5":"78.3","video-to-text R@1":"53.7","video-to-text R@10":"84.1","video-to-text R@5":"77.5"},"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/video-retrieval-on-msr-vtt","task":"Video Retrieval","dataset_variant":"MSR-VTT","rows":40,"metrics":["text-to-video R@1","text-to-video R@5","text-to-video R@10","text-to-video Mean Rank","text-to-video Median Rank","video-to-text R@1","video-to-text R@5","video-to-text R@10","video-to-text Median Rank","video-to-text Mean Rank","text-to-video MedianR","text-to-videoMedian Rank"],"first_row_in_archive_order":{"model":"GRAM","paper":"/paper/gramian-multimodal-representation-learning","metrics":{"text-to-video R@1":"64","text-to-video R@10":"89.3","video-to-text R@1":"64.8","video-to-text R@10":"91.5"},"code_links":[{"title":"ispamm/GRAM","url":"https://github.com/ispamm/GRAM"},{"title":"luigisigillo/gwit","url":"https://github.com/luigisigillo/gwit"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-captioning-on-msr-vtt-1","task":"Video Captioning","dataset_variant":"MSR-VTT","rows":24,"metrics":["CIDEr","METEOR","ROUGE-L","BLEU-4","GS"],"first_row_in_archive_order":{"model":"mPLUG-2","paper":"/paper/mplug-2-a-modularized-multi-modal-foundation","metrics":{"BLEU-4":"57.8","CIDEr":"80.0","METEOR":"34.9","ROUGE-L":"70.1"},"code_links":[{"title":"modelscope/modelscope","url":"https://github.com/modelscope/modelscope"},{"title":"x-plug/mplug-owl","url":"https://github.com/x-plug/mplug-owl"},{"title":"alibaba/AliceMind","url":"https://github.com/alibaba/AliceMind"},{"title":"X-PLUG/mPLUG-2","url":"https://github.com/X-PLUG/mPLUG-2"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-to-video-generation-on-msr-vtt","task":"Text-to-Video Generation","dataset_variant":"MSR-VTT","rows":18,"metrics":["FVD","CLIPSIM","CLIP-FID","FID"],"first_row_in_archive_order":{"model":"Snap Video (512x288)","paper":"/paper/snap-video-scaled-spatiotemporal-transformers","metrics":{"CLIP-FID":"9.35","CLIPSIM":"0.2793","FVD":"104.0"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-to-video-retrieval-on-msr-vtt","task":"Text to Video Retrieval","dataset_variant":"MSR-VTT","rows":1,"metrics":["text-to-video R@1"],"first_row_in_archive_order":{"model":"CLIP4Clip","paper":"/paper/clip4clip-an-empirical-study-of-clip-for-end","metrics":{"text-to-video R@1":"44.5"},"code_links":[{"title":"towhee-io/towhee","url":"https://github.com/towhee-io/towhee"},{"title":"ArrowLuo/CLIP4Clip","url":"https://github.com/ArrowLuo/CLIP4Clip"},{"title":"roudimit/AVLnet","url":"https://github.com/roudimit/AVLnet"},{"title":"facebookresearch/EgoTV","url":"https://github.com/facebookresearch/EgoTV"},{"title":"willard-yuan/video-text-retrieval-papers","url":"https://github.com/willard-yuan/video-text-retrieval-papers"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-generation-on-msr-vtt","task":"Video Generation","dataset_variant":"MSR-VTT","rows":1,"metrics":["FVD16","Inception score"],"first_row_in_archive_order":{"model":"VideoAssembler (Zero-Shot, 256x256, class-conditional)","paper":"/paper/videoassembler-identity-consistent-video","metrics":{"FVD16":"252","Inception score":"15.79"},"code_links":[{"title":"gulucaptain/videoassembler","url":"https://github.com/gulucaptain/videoassembler"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-question-answering-on-msr-vtt","task":"Video Question Answering","dataset_variant":"MSR-VTT","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"LocVLM-Vid-B","paper":"/paper/learning-to-localize-objects-improves-spatial","metrics":{"Accuracy":"51.2"},"code_links":[{"title":"kahnchana/locvlm","url":"https://github.com/kahnchana/locvlm"}]},"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":2,"rows_per_page":100,"shown":100,"of":117,"counts":{"papers_with_a_benchmark_row":117,"with_a_code_link":92,"where_syntology_ran_a_sample":49,"not_listed_spam_title":0,"listed":117,"listed_where_code_ran":49,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":39,"every_run_a_failure_of_syntologys_instrument":10,"listed_with_a_run_with_no_instrument_failure":39,"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/make-your-training-flexible-towards","slug":"make-your-training-flexible-towards","title":"Make Your Training Flexible: Towards Deployment-Efficient Video Models","date":"2025-03-18","arxiv_id":"2503.14237","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":17,"samples_constructed":0,"samples_ran_checked":17,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":6,"official":{"repos":["opengvlab/fluxvit"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":17,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/make-your-training-flexible-towards#ran","syntology_url":"https://syntology.ai/paper/2503.14237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.14237"}}}},{"paper":"/paper/gramian-multimodal-representation-learning","slug":"gramian-multimodal-representation-learning","title":"Gramian Multimodal Representation Learning and Alignment","date":"2024-12-16","arxiv_id":"2412.11959","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":3,"samples_unverified":5,"pointer_only_for_licence":1,"official":{"repos":["ispamm/GRAM"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/gramian-multimodal-representation-learning#ran","syntology_url":"https://syntology.ai/paper/2412.11959","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.11959"}}}},{"paper":"/paper/learning-to-localize-objects-improves-spatial","slug":"learning-to-localize-objects-improves-spatial","title":"Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs","date":"2024-04-11","arxiv_id":"2404.07449","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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":3,"code_links":2,"syntology":null},{"paper":"/paper/vid-tldr-training-free-token-merging-for","slug":"vid-tldr-training-free-token-merging-for","title":"vid-TLDR: Training Free Token merging for Light-weight Video Transformer","date":"2024-03-20","arxiv_id":"2403.13347","rows_on_this_dataset":2,"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":0,"official":{"repos":["mlvlab/vid-tldr"],"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/vid-tldr-training-free-token-merging-for#ran","syntology_url":"https://syntology.ai/paper/2403.13347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13347"}}}},{"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/multi-granularity-correspondence-learning-1","slug":"multi-granularity-correspondence-learning-1","title":"Multi-granularity Correspondence Learning from Long-term Noisy Videos","date":"2024-01-30","arxiv_id":"2401.16702","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":2,"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/multi-granularity-correspondence-learning-1#ran","syntology_url":"https://syntology.ai/paper/2401.16702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.16702"}}}},{"paper":"/paper/holistic-features-are-almost-sufficient-for","slug":"holistic-features-are-almost-sufficient-for","title":"Holistic Features are almost Sufficient for Text-to-Video Retrieval","date":"2024-01-01","arxiv_id":null,"rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/towards-efficient-and-effective-text-to-video","slug":"towards-efficient-and-effective-text-to-video","title":"Towards Efficient and Effective Text-to-Video Retrieval with Coarse-to-Fine Visual Representation Learning","date":"2024-01-01","arxiv_id":"2401.00701","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-recipe-for-scaling-up-text-to-video","slug":"a-recipe-for-scaling-up-text-to-video","title":"A Recipe for Scaling up Text-to-Video Generation with Text-free Videos","date":"2023-12-25","arxiv_id":"2312.15770","rows_on_this_dataset":1,"code_links":1,"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":1,"code_links":0,"syntology":null},{"paper":"/paper/hierarchical-spatio-temporal-decoupling-for","slug":"hierarchical-spatio-temporal-decoupling-for","title":"Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation","date":"2023-12-07","arxiv_id":"2312.04483","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rtq-rethinking-video-language-understanding","slug":"rtq-rethinking-video-language-understanding","title":"RTQ: Rethinking Video-language Understanding Based on Image-text Model","date":"2023-12-01","arxiv_id":"2312.00347","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"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/side4video-spatial-temporal-side-network-for","slug":"side4video-spatial-temporal-side-network-for","title":"Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer Learning","date":"2023-11-27","arxiv_id":"2311.15769","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"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":1,"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":2,"code_links":0,"syntology":null},{"paper":"/paper/howtocaption-prompting-llms-to-transform","slug":"howtocaption-prompting-llms-to-transform","title":"HowToCaption: Prompting LLMs to Transform Video Annotations at Scale","date":"2023-10-07","arxiv_id":"2310.04900","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":5,"official":{"repos":["ninatu/howtocaption"],"state":"official (archive's flag): 4 ran","n_ran":4,"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/howtocaption-prompting-llms-to-transform#ran","syntology_url":"https://syntology.ai/paper/2310.04900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04900"}}}},{"paper":"/paper/icocap-improving-video-captioning-by","slug":"icocap-improving-video-captioning-by","title":"IcoCap: Improving Video Captioning by Compounding Images","date":"2023-10-05","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/languagebind-extending-video-language","slug":"languagebind-extending-video-language","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","date":"2023-10-03","arxiv_id":"2310.01852","rows_on_this_dataset":2,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":3,"official":{"repos":["pku-yuangroup/languagebind"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/languagebind-extending-video-language#ran","syntology_url":"https://syntology.ai/paper/2310.01852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01852"}}}},{"paper":"/paper/prototype-based-aleatoric-uncertainty-1","slug":"prototype-based-aleatoric-uncertainty-1","title":"Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval","date":"2023-09-29","arxiv_id":"2309.17093","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":17,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":8,"samples_unverified":2,"pointer_only_for_licence":8,"official":{"repos":["leolee99/pau"],"state":"official (archive's flag): 17 ran","n_ran":17,"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/prototype-based-aleatoric-uncertainty-1#ran","syntology_url":"https://syntology.ai/paper/2309.17093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17093"}}}},{"paper":"/paper/one-for-all-video-conversation-is-feasible","slug":"one-for-all-video-conversation-is-feasible","title":"BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning","date":"2023-09-27","arxiv_id":"2309.15785","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":2,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["farewellthree/BT-Adapter"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/one-for-all-video-conversation-is-feasible#ran","syntology_url":"https://syntology.ai/paper/2309.15785","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.15785"}}}},{"paper":"/paper/show-1-marrying-pixel-and-latent-diffusion","slug":"show-1-marrying-pixel-and-latent-diffusion","title":"Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation","date":"2023-09-27","arxiv_id":"2309.15818","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":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["showlab/show-1"],"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/show-1-marrying-pixel-and-latent-diffusion#ran","syntology_url":"https://syntology.ai/paper/2309.15818","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.15818"}}}},{"paper":"/paper/accurate-and-fast-compressed-video-captioning","slug":"accurate-and-fast-compressed-video-captioning","title":"Accurate and Fast Compressed Video Captioning","date":"2023-09-22","arxiv_id":"2309.12867","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":10,"samples_constructed":8,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["acherstyx/CoCap"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":8,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/accurate-and-fast-compressed-video-captioning#ran","syntology_url":"https://syntology.ai/paper/2309.12867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12867"}}}},{"paper":"/paper/dual-modal-attention-enhanced-text-video","slug":"dual-modal-attention-enhanced-text-video","title":"Dual-Modal Attention-Enhanced Text-Video Retrieval with Triplet Partial Margin Contrastive Learning","date":"2023-09-20","arxiv_id":"2309.11082","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unified-coarse-to-fine-alignment-for-video","slug":"unified-coarse-to-fine-alignment-for-video","title":"Unified Coarse-to-Fine Alignment for Video-Text Retrieval","date":"2023-09-18","arxiv_id":"2309.10091","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":4,"samples_unverified":3,"pointer_only_for_licence":4,"official":{"repos":["ziyang412/ucofia"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unified-coarse-to-fine-alignment-for-video#ran","syntology_url":"https://syntology.ai/paper/2309.10091","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.10091"}}}},{"paper":"/paper/modelscope-text-to-video-technical-report","slug":"modelscope-text-to-video-technical-report","title":"ModelScope Text-to-Video Technical Report","date":"2023-08-12","arxiv_id":"2308.06571","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":1,"official":{"repos":["exponentialml/text-to-video-finetuning"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/modelscope-text-to-video-technical-report#ran","syntology_url":"https://syntology.ai/paper/2308.06571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06571"}}}},{"paper":"/paper/audio-enhanced-text-to-video-retrieval-using","slug":"audio-enhanced-text-to-video-retrieval-using","title":"Audio-Enhanced Text-to-Video Retrieval using Text-Conditioned Feature Alignment","date":"2023-07-24","arxiv_id":"2307.12964","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/cosa-concatenated-sample-pretrained-vision","slug":"cosa-concatenated-sample-pretrained-vision","title":"COSA: Concatenated Sample Pretrained Vision-Language Foundation Model","date":"2023-06-15","arxiv_id":"2306.09085","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/videocomposer-compositional-video-synthesis","slug":"videocomposer-compositional-video-synthesis","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","date":"2023-06-03","arxiv_id":"2306.02018","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":16,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":5,"samples_unverified":5,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/videocomposer-compositional-video-synthesis#ran","syntology_url":"https://syntology.ai/paper/2306.02018","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02018"}}}},{"paper":"/paper/vast-a-vision-audio-subtitle-text-omni-1","slug":"vast-a-vision-audio-subtitle-text-omni-1","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","date":"2023-05-29","arxiv_id":"2305.18500","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":42,"samples_ran":35,"samples_constructed":4,"samples_ran_checked":25,"samples_ran_instrument_failed":10,"samples_unverified":7,"pointer_only_for_licence":8,"official":{"repos":["txh-mercury/vast"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":4,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vast-a-vision-audio-subtitle-text-omni-1#ran","syntology_url":"https://syntology.ai/paper/2305.18500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18500"}}}},{"paper":"/paper/vlab-enhancing-video-language-pre-training-by","slug":"vlab-enhancing-video-language-pre-training-by","title":"VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending","date":"2023-05-22","arxiv_id":"2305.13167","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/imagebind-one-embedding-space-to-bind-them","slug":"imagebind-one-embedding-space-to-bind-them","title":"ImageBind: One Embedding Space To Bind Them All","date":"2023-05-09","arxiv_id":"2305.05665","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":34,"samples_ran":24,"samples_constructed":14,"samples_ran_checked":21,"samples_ran_instrument_failed":3,"samples_unverified":10,"pointer_only_for_licence":32,"official":{"repos":["facebookresearch/imagebind"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":10,"n_ran_no_instrument_failure":15,"n_unverified":7,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/imagebind-one-embedding-space-to-bind-them#ran","syntology_url":"https://syntology.ai/paper/2305.05665","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.05665"}}}},{"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/valor-vision-audio-language-omni-perception","slug":"valor-vision-audio-language-omni-perception","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","date":"2023-04-17","arxiv_id":"2304.08345","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/mammut-a-simple-architecture-for-joint","slug":"mammut-a-simple-architecture-for-joint","title":"MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks","date":"2023-03-29","arxiv_id":"2303.16839","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":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mammut-a-simple-architecture-for-joint#ran","syntology_url":"https://syntology.ai/paper/2303.16839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16839"}}}},{"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":2,"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/sem-pos-grammatically-and-semantically","slug":"sem-pos-grammatically-and-semantically","title":"SEM-POS: Grammatically and Semantically Correct Video Captioning","date":"2023-03-26","arxiv_id":"2303.14829","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/video-text-as-game-players-hierarchical","slug":"video-text-as-game-players-hierarchical","title":"Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning","date":"2023-03-25","arxiv_id":"2303.14369","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":12,"samples_constructed":7,"samples_ran_checked":11,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["jpthu17/HBI"],"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":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-text-as-game-players-hierarchical#ran","syntology_url":"https://syntology.ai/paper/2303.14369","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14369"}}}},{"paper":"/paper/meltr-meta-loss-transformer-for-learning-to","slug":"meltr-meta-loss-transformer-for-learning-to","title":"MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models","date":"2023-03-23","arxiv_id":"2303.13009","rows_on_this_dataset":7,"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":0,"official":{"repos":["mlvlab/MELTR"],"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/meltr-meta-loss-transformer-for-learning-to#ran","syntology_url":"https://syntology.ai/paper/2303.13009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.13009"}}}},{"paper":"/paper/text-with-knowledge-graph-augmented","slug":"text-with-knowledge-graph-augmented","title":"Text with Knowledge Graph Augmented Transformer for Video Captioning","date":"2023-03-22","arxiv_id":"2303.12423","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/diffusionret-generative-text-video-retrieval","slug":"diffusionret-generative-text-video-retrieval","title":"DiffusionRet: Generative Text-Video Retrieval with Diffusion Model","date":"2023-03-17","arxiv_id":"2303.09867","rows_on_this_dataset":2,"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":["jpthu17/diffusionret"],"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/diffusionret-generative-text-video-retrieval#ran","syntology_url":"https://syntology.ai/paper/2303.09867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09867"}}}},{"paper":"/paper/multi-efficient-video-and-language","slug":"multi-efficient-video-and-language","title":"MuLTI: Efficient Video-and-Language Understanding with Text-Guided MultiWay-Sampler and Multiple Choice Modeling","date":"2023-03-10","arxiv_id":"2303.05707","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/vid2seq-large-scale-pretraining-of-a-visual","slug":"vid2seq-large-scale-pretraining-of-a-visual","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","date":"2023-02-27","arxiv_id":"2302.14115","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/video-text-retrieval-by-supervised-multi","slug":"video-text-retrieval-by-supervised-multi","title":"Video-Text Retrieval by Supervised Sparse Multi-Grained Learning","date":"2023-02-19","arxiv_id":"2302.09473","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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":3,"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/revisiting-temporal-modeling-for-clip-based","slug":"revisiting-temporal-modeling-for-clip-based","title":"Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring","date":"2023-01-26","arxiv_id":"2301.11116","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pidro-parallel-isomeric-attention-with","slug":"pidro-parallel-isomeric-attention-with","title":"PIDRo: Parallel Isomeric Attention with Dynamic Routing for Text-Video Retrieval","date":"2023-01-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/cap4video-what-can-auxiliary-captions-do-for","slug":"cap4video-what-can-auxiliary-captions-do-for","title":"Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?","date":"2022-12-31","arxiv_id":"2301.00184","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":25,"samples_ran":20,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":11,"samples_unverified":5,"pointer_only_for_licence":11,"official":{"repos":["whwu95/Cap4Video"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cap4video-what-can-auxiliary-captions-do-for#ran","syntology_url":"https://syntology.ai/paper/2301.00184","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00184"}}}},{"paper":"/paper/hitea-hierarchical-temporal-aware-video","slug":"hitea-hierarchical-temporal-aware-video","title":"HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training","date":"2022-12-30","arxiv_id":"2212.14546","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"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":2,"code_links":0,"syntology":null},{"paper":"/paper/vindlu-a-recipe-for-effective-video-and","slug":"vindlu-a-recipe-for-effective-video-and","title":"VindLU: A Recipe for Effective Video-and-Language Pretraining","date":"2022-12-09","arxiv_id":"2212.05051","rows_on_this_dataset":1,"code_links":1,"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":2,"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/masked-contrastive-pre-training-for-efficient","slug":"masked-contrastive-pre-training-for-efficient","title":"Masked Contrastive Pre-Training for Efficient Video-Text Retrieval","date":"2022-12-02","arxiv_id":"2212.00986","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/seeing-what-you-miss-vision-language-pre","slug":"seeing-what-you-miss-vision-language-pre","title":"Seeing What You Miss: Vision-Language Pre-training with Semantic Completion Learning","date":"2022-11-24","arxiv_id":"2211.13437","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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":1,"code_links":1,"syntology":null},{"paper":"/paper/x-2-vlm-all-in-one-pre-trained-model-for","slug":"x-2-vlm-all-in-one-pre-trained-model-for","title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks","date":"2022-11-22","arxiv_id":"2211.12402","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":6,"official":{"repos":["zengyan-97/x2-vlm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/x-2-vlm-all-in-one-pre-trained-model-for#ran","syntology_url":"https://syntology.ai/paper/2211.12402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.12402"}}}},{"paper":"/paper/expectation-maximization-contrastive-learning","slug":"expectation-maximization-contrastive-learning","title":"Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations","date":"2022-11-21","arxiv_id":"2211.11427","rows_on_this_dataset":3,"code_links":4,"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":0,"official":{"repos":["jpthu17/emcl"],"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":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/expectation-maximization-contrastive-learning#ran","syntology_url":"https://syntology.ai/paper/2211.11427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.11427"}}}},{"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":1,"code_links":0,"syntology":null},{"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/omnivl-one-foundation-model-for-image","slug":"omnivl-one-foundation-model-for-image","title":"OmniVL:One Foundation Model for Image-Language and Video-Language Tasks","date":"2022-09-15","arxiv_id":"2209.07526","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/clip-vip-adapting-pre-trained-image-text","slug":"clip-vip-adapting-pre-trained-image-text","title":"CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment","date":"2022-09-14","arxiv_id":"2209.06430","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":4,"official":{"repos":["microsoft/xpretrain"],"state":"official (archive's flag): 4 ran","n_ran":4,"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/clip-vip-adapting-pre-trained-image-text#ran","syntology_url":"https://syntology.ai/paper/2209.06430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.06430"}}}},{"paper":"/paper/an-empirical-study-of-end-to-end-video","slug":"an-empirical-study-of-end-to-end-video","title":"An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling","date":"2022-09-04","arxiv_id":"2209.01540","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/diverse-video-captioning-by-adaptive-spatio","slug":"diverse-video-captioning-by-adaptive-spatio","title":"Diverse Video Captioning by Adaptive Spatio-temporal Attention","date":"2022-08-19","arxiv_id":"2208.09266","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/clover-towards-a-unified-video-language","slug":"clover-towards-a-unified-video-language","title":"Clover: Towards A Unified Video-Language Alignment and Fusion Model","date":"2022-07-16","arxiv_id":"2207.07885","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/ts2-net-token-shift-and-selection-transformer","slug":"ts2-net-token-shift-and-selection-transformer","title":"TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval","date":"2022-07-16","arxiv_id":"2207.07852","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":4,"official":{"repos":["yuqi657/ts2_net"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ts2-net-token-shift-and-selection-transformer#ran","syntology_url":"https://syntology.ai/paper/2207.07852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.07852"}}}},{"paper":"/paper/x-clip-end-to-end-multi-grained-contrastive","slug":"x-clip-end-to-end-multi-grained-contrastive","title":"X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval","date":"2022-07-15","arxiv_id":"2207.07285","rows_on_this_dataset":1,"code_links":3,"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":1,"official":{"repos":["xuguohai/X-CLIP"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/x-clip-end-to-end-multi-grained-contrastive#ran","syntology_url":"https://syntology.ai/paper/2207.07285","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.07285"}}}},{"paper":"/paper/lat-latent-translation-with-cycle-consistency","slug":"lat-latent-translation-with-cycle-consistency","title":"LaT: Latent Translation with Cycle-Consistency for Video-Text Retrieval","date":"2022-07-11","arxiv_id":"2207.04858","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/rome-role-aware-mixture-of-expert-transformer","slug":"rome-role-aware-mixture-of-expert-transformer","title":"RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval","date":"2022-06-26","arxiv_id":"2206.12845","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/revealing-single-frame-bias-for-video-and","slug":"revealing-single-frame-bias-for-video-and","title":"Revealing Single Frame Bias for Video-and-Language Learning","date":"2022-06-07","arxiv_id":"2206.03428","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":4,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["jayleicn/singularity"],"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/revealing-single-frame-bias-for-video-and#ran","syntology_url":"https://syntology.ai/paper/2206.03428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.03428"}}}},{"paper":"/paper/git-a-generative-image-to-text-transformer","slug":"git-a-generative-image-to-text-transformer","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","date":"2022-05-27","arxiv_id":"2205.14100","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":14,"samples_ran_instrument_failed":0,"samples_unverified":7,"pointer_only_for_licence":0,"official":{"repos":["microsoft/GenerativeImage2Text"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":7,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/git-a-generative-image-to-text-transformer#ran","syntology_url":"https://syntology.ai/paper/2205.14100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14100"}}}},{"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":1,"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/centerclip-token-clustering-for-efficient","slug":"centerclip-token-clustering-for-efficient","title":"CenterCLIP: Token Clustering for Efficient Text-Video Retrieval","date":"2022-05-02","arxiv_id":"2205.00823","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":1,"official":{"repos":["mzhaoshuai/CenterCLIP"],"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/centerclip-token-clustering-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2205.00823","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.00823"}}}},{"paper":"/paper/miles-visual-bert-pre-training-with-injected","slug":"miles-visual-bert-pre-training-with-injected","title":"MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval","date":"2022-04-26","arxiv_id":"2204.12408","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cots-collaborative-two-stream-vision-language","slug":"cots-collaborative-two-stream-vision-language","title":"COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval","date":"2022-04-15","arxiv_id":"2204.07441","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/hunyuan-tvr-for-text-video-retrivial","slug":"hunyuan-tvr-for-text-video-retrivial","title":"Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations","date":"2022-04-07","arxiv_id":"2204.03382","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/learning-audio-video-modalities-from-image","slug":"learning-audio-video-modalities-from-image","title":"Learning Audio-Video Modalities from Image Captions","date":"2022-04-01","arxiv_id":"2204.00679","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/socratic-models-composing-zero-shot","slug":"socratic-models-composing-zero-shot","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","date":"2022-04-01","arxiv_id":"2204.00598","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/x-pool-cross-modal-language-video-attention","slug":"x-pool-cross-modal-language-video-attention","title":"X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval","date":"2022-03-28","arxiv_id":"2203.15086","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":2,"official":{"repos":["layer6ai-labs/xpool"],"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/x-pool-cross-modal-language-video-attention#ran","syntology_url":"https://syntology.ai/paper/2203.15086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15086"}}}},{"paper":"/paper/all-in-one-exploring-unified-video-language","slug":"all-in-one-exploring-unified-video-language","title":"All in One: Exploring Unified Video-Language Pre-training","date":"2022-03-14","arxiv_id":"2203.07303","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/disentangled-representation-learning-for-text","slug":"disentangled-representation-learning-for-text","title":"Disentangled Representation Learning for Text-Video Retrieval","date":"2022-03-14","arxiv_id":"2203.07111","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":5,"samples_unverified":2,"pointer_only_for_licence":4,"official":{"repos":["foolwood/DRL"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/disentangled-representation-learning-for-text#ran","syntology_url":"https://syntology.ai/paper/2203.07111","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.07111"}}}},{"paper":"/paper/mdmmt-2-multidomain-multimodal-transformer","slug":"mdmmt-2-multidomain-multimodal-transformer","title":"MDMMT-2: Multidomain Multimodal Transformer for Video Retrieval, One More Step Towards Generalization","date":"2022-03-14","arxiv_id":"2203.07086","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/end-to-end-generative-pretraining-for","slug":"end-to-end-generative-pretraining-for","title":"End-to-end Generative Pretraining for Multimodal Video Captioning","date":"2022-01-20","arxiv_id":"2201.08264","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/bridgeformer-bridging-video-text-retrieval","slug":"bridgeformer-bridging-video-text-retrieval","title":"Bridging Video-text Retrieval with Multiple Choice Questions","date":"2022-01-13","arxiv_id":"2201.04850","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":24,"samples_ran":13,"samples_constructed":8,"samples_ran_checked":9,"samples_ran_instrument_failed":4,"samples_unverified":11,"pointer_only_for_licence":6,"official":{"repos":["tencentarc/mcq"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bridgeformer-bridging-video-text-retrieval#ran","syntology_url":"https://syntology.ai/paper/2201.04850","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.04850"}}}},{"paper":"/paper/cross-modal-retrieval-with-querybank","slug":"cross-modal-retrieval-with-querybank","title":"Cross Modal Retrieval with Querybank Normalisation","date":"2021-12-23","arxiv_id":"2112.12777","rows_on_this_dataset":1,"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":1,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["ioanacroi/qb-norm"],"state":"official (archive's flag): 2 ran","n_ran":2,"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/cross-modal-retrieval-with-querybank#ran","syntology_url":"https://syntology.ai/paper/2112.12777","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.12777"}}}},{"paper":"/paper/align-and-prompt-video-and-language-pre","slug":"align-and-prompt-video-and-language-pre","title":"Align and Prompt: Video-and-Language Pre-training with Entity Prompts","date":"2021-12-17","arxiv_id":"2112.09583","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/lightweight-attentional-feature-fusion-for","slug":"lightweight-attentional-feature-fusion-for","title":"Lightweight Attentional Feature Fusion: A New Baseline for Text-to-Video Retrieval","date":"2021-12-03","arxiv_id":"2112.01832","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/object-aware-video-language-pre-training-for","slug":"object-aware-video-language-pre-training-for","title":"Object-aware Video-language Pre-training for Retrieval","date":"2021-12-01","arxiv_id":"2112.00656","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/clip-meets-video-captioners-attribute-aware","slug":"clip-meets-video-captioners-attribute-aware","title":"CLIP Meets Video Captioning: Concept-Aware Representation Learning Does Matter","date":"2021-11-30","arxiv_id":"2111.15162","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/nuwa-visual-synthesis-pre-training-for-neural","slug":"nuwa-visual-synthesis-pre-training-for-neural","title":"NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion","date":"2021-11-24","arxiv_id":"2111.12417","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":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/nuwa-visual-synthesis-pre-training-for-neural#ran","syntology_url":"https://syntology.ai/paper/2111.12417","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.12417"}}}},{"paper":"/paper/violet-end-to-end-video-language-transformers","slug":"violet-end-to-end-video-language-transformers","title":"VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling","date":"2021-11-24","arxiv_id":"2111.12681","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":2,"official":{"repos":["tsujuifu/pytorch_violet"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/violet-end-to-end-video-language-transformers#ran","syntology_url":"https://syntology.ai/paper/2111.12681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.12681"}}}},{"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/advancing-high-resolution-video-language","slug":"advancing-high-resolution-video-language","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","date":"2021-11-19","arxiv_id":"2111.10337","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/clip2tv-an-empirical-study-on-transformer","slug":"clip2tv-an-empirical-study-on-transformer","title":"CLIP2TV: Align, Match and Distill for Video-Text Retrieval","date":"2021-11-10","arxiv_id":"2111.05610","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/video-and-text-matching-with-conditioned","slug":"video-and-text-matching-with-conditioned","title":"Video and Text Matching with Conditioned Embeddings","date":"2021-10-21","arxiv_id":"2110.11298","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/videoclip-contrastive-pre-training-for-zero","slug":"videoclip-contrastive-pre-training-for-zero","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","date":"2021-09-28","arxiv_id":"2109.14084","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/improving-video-text-retrieval-by-multi","slug":"improving-video-text-retrieval-by-multi","title":"Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss","date":"2021-09-09","arxiv_id":"2109.04290","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/taco-token-aware-cascade-contrastive-learning","slug":"taco-token-aware-cascade-contrastive-learning","title":"TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment","date":"2021-08-23","arxiv_id":"2108.09980","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/clip2video-mastering-video-text-retrieval-via","slug":"clip2video-mastering-video-text-retrieval-via","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","date":"2021-06-21","arxiv_id":"2106.11097","rows_on_this_dataset":2,"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":["CryhanFang/CLIP2Video"],"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/clip2video-mastering-video-text-retrieval-via#ran","syntology_url":"https://syntology.ai/paper/2106.11097","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11097"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/make-your-training-flexible-towards","slug":"make-your-training-flexible-towards","title":"Make Your Training Flexible: Towards Deployment-Efficient Video Models","date":"2025-03-18","arxiv_id":"2503.14237","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":17,"samples_constructed":0,"samples_ran_checked":17,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":6,"official":{"repos":["opengvlab/fluxvit"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":17,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/make-your-training-flexible-towards#ran","syntology_url":"https://syntology.ai/paper/2503.14237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.14237"}}}},{"paper":"/paper/gramian-multimodal-representation-learning","slug":"gramian-multimodal-representation-learning","title":"Gramian Multimodal Representation Learning and Alignment","date":"2024-12-16","arxiv_id":"2412.11959","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":3,"samples_unverified":5,"pointer_only_for_licence":1,"official":{"repos":["ispamm/GRAM"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/gramian-multimodal-representation-learning#ran","syntology_url":"https://syntology.ai/paper/2412.11959","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.11959"}}}},{"paper":"/paper/learning-to-localize-objects-improves-spatial","slug":"learning-to-localize-objects-improves-spatial","title":"Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs","date":"2024-04-11","arxiv_id":"2404.07449","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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":3,"code_links":2,"syntology":null},{"paper":"/paper/vid-tldr-training-free-token-merging-for","slug":"vid-tldr-training-free-token-merging-for","title":"vid-TLDR: Training Free Token merging for Light-weight Video Transformer","date":"2024-03-20","arxiv_id":"2403.13347","rows_on_this_dataset":2,"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":0,"official":{"repos":["mlvlab/vid-tldr"],"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/vid-tldr-training-free-token-merging-for#ran","syntology_url":"https://syntology.ai/paper/2403.13347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13347"}}}},{"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/multi-granularity-correspondence-learning-1","slug":"multi-granularity-correspondence-learning-1","title":"Multi-granularity Correspondence Learning from Long-term Noisy Videos","date":"2024-01-30","arxiv_id":"2401.16702","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":2,"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/multi-granularity-correspondence-learning-1#ran","syntology_url":"https://syntology.ai/paper/2401.16702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.16702"}}}},{"paper":"/paper/holistic-features-are-almost-sufficient-for","slug":"holistic-features-are-almost-sufficient-for","title":"Holistic Features are almost Sufficient for Text-to-Video Retrieval","date":"2024-01-01","arxiv_id":null,"rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/towards-efficient-and-effective-text-to-video","slug":"towards-efficient-and-effective-text-to-video","title":"Towards Efficient and Effective Text-to-Video Retrieval with Coarse-to-Fine Visual Representation Learning","date":"2024-01-01","arxiv_id":"2401.00701","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-recipe-for-scaling-up-text-to-video","slug":"a-recipe-for-scaling-up-text-to-video","title":"A Recipe for Scaling up Text-to-Video Generation with Text-free Videos","date":"2023-12-25","arxiv_id":"2312.15770","rows_on_this_dataset":1,"code_links":1,"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":1,"code_links":0,"syntology":null},{"paper":"/paper/hierarchical-spatio-temporal-decoupling-for","slug":"hierarchical-spatio-temporal-decoupling-for","title":"Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation","date":"2023-12-07","arxiv_id":"2312.04483","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rtq-rethinking-video-language-understanding","slug":"rtq-rethinking-video-language-understanding","title":"RTQ: Rethinking Video-language Understanding Based on Image-text Model","date":"2023-12-01","arxiv_id":"2312.00347","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"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/side4video-spatial-temporal-side-network-for","slug":"side4video-spatial-temporal-side-network-for","title":"Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer Learning","date":"2023-11-27","arxiv_id":"2311.15769","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"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":1,"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":2,"code_links":0,"syntology":null},{"paper":"/paper/howtocaption-prompting-llms-to-transform","slug":"howtocaption-prompting-llms-to-transform","title":"HowToCaption: Prompting LLMs to Transform Video Annotations at Scale","date":"2023-10-07","arxiv_id":"2310.04900","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":5,"official":{"repos":["ninatu/howtocaption"],"state":"official (archive's flag): 4 ran","n_ran":4,"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/howtocaption-prompting-llms-to-transform#ran","syntology_url":"https://syntology.ai/paper/2310.04900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04900"}}}},{"paper":"/paper/icocap-improving-video-captioning-by","slug":"icocap-improving-video-captioning-by","title":"IcoCap: Improving Video Captioning by Compounding Images","date":"2023-10-05","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/languagebind-extending-video-language","slug":"languagebind-extending-video-language","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","date":"2023-10-03","arxiv_id":"2310.01852","rows_on_this_dataset":2,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":3,"official":{"repos":["pku-yuangroup/languagebind"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/languagebind-extending-video-language#ran","syntology_url":"https://syntology.ai/paper/2310.01852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01852"}}}},{"paper":"/paper/prototype-based-aleatoric-uncertainty-1","slug":"prototype-based-aleatoric-uncertainty-1","title":"Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval","date":"2023-09-29","arxiv_id":"2309.17093","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":17,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":8,"samples_unverified":2,"pointer_only_for_licence":8,"official":{"repos":["leolee99/pau"],"state":"official (archive's flag): 17 ran","n_ran":17,"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/prototype-based-aleatoric-uncertainty-1#ran","syntology_url":"https://syntology.ai/paper/2309.17093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17093"}}}},{"paper":"/paper/one-for-all-video-conversation-is-feasible","slug":"one-for-all-video-conversation-is-feasible","title":"BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning","date":"2023-09-27","arxiv_id":"2309.15785","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":2,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["farewellthree/BT-Adapter"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/one-for-all-video-conversation-is-feasible#ran","syntology_url":"https://syntology.ai/paper/2309.15785","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.15785"}}}},{"paper":"/paper/show-1-marrying-pixel-and-latent-diffusion","slug":"show-1-marrying-pixel-and-latent-diffusion","title":"Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation","date":"2023-09-27","arxiv_id":"2309.15818","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":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["showlab/show-1"],"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/show-1-marrying-pixel-and-latent-diffusion#ran","syntology_url":"https://syntology.ai/paper/2309.15818","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.15818"}}}},{"paper":"/paper/accurate-and-fast-compressed-video-captioning","slug":"accurate-and-fast-compressed-video-captioning","title":"Accurate and Fast Compressed Video Captioning","date":"2023-09-22","arxiv_id":"2309.12867","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":10,"samples_constructed":8,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["acherstyx/CoCap"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":8,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/accurate-and-fast-compressed-video-captioning#ran","syntology_url":"https://syntology.ai/paper/2309.12867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12867"}}}},{"paper":"/paper/dual-modal-attention-enhanced-text-video","slug":"dual-modal-attention-enhanced-text-video","title":"Dual-Modal Attention-Enhanced Text-Video Retrieval with Triplet Partial Margin Contrastive Learning","date":"2023-09-20","arxiv_id":"2309.11082","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unified-coarse-to-fine-alignment-for-video","slug":"unified-coarse-to-fine-alignment-for-video","title":"Unified Coarse-to-Fine Alignment for Video-Text Retrieval","date":"2023-09-18","arxiv_id":"2309.10091","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":4,"samples_unverified":3,"pointer_only_for_licence":4,"official":{"repos":["ziyang412/ucofia"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unified-coarse-to-fine-alignment-for-video#ran","syntology_url":"https://syntology.ai/paper/2309.10091","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.10091"}}}},{"paper":"/paper/modelscope-text-to-video-technical-report","slug":"modelscope-text-to-video-technical-report","title":"ModelScope Text-to-Video Technical Report","date":"2023-08-12","arxiv_id":"2308.06571","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":1,"official":{"repos":["exponentialml/text-to-video-finetuning"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/modelscope-text-to-video-technical-report#ran","syntology_url":"https://syntology.ai/paper/2308.06571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06571"}}}},{"paper":"/paper/audio-enhanced-text-to-video-retrieval-using","slug":"audio-enhanced-text-to-video-retrieval-using","title":"Audio-Enhanced Text-to-Video Retrieval using Text-Conditioned Feature Alignment","date":"2023-07-24","arxiv_id":"2307.12964","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/cosa-concatenated-sample-pretrained-vision","slug":"cosa-concatenated-sample-pretrained-vision","title":"COSA: Concatenated Sample Pretrained Vision-Language Foundation Model","date":"2023-06-15","arxiv_id":"2306.09085","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/videocomposer-compositional-video-synthesis","slug":"videocomposer-compositional-video-synthesis","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","date":"2023-06-03","arxiv_id":"2306.02018","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":16,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":5,"samples_unverified":5,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/videocomposer-compositional-video-synthesis#ran","syntology_url":"https://syntology.ai/paper/2306.02018","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02018"}}}},{"paper":"/paper/vast-a-vision-audio-subtitle-text-omni-1","slug":"vast-a-vision-audio-subtitle-text-omni-1","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","date":"2023-05-29","arxiv_id":"2305.18500","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":42,"samples_ran":35,"samples_constructed":4,"samples_ran_checked":25,"samples_ran_instrument_failed":10,"samples_unverified":7,"pointer_only_for_licence":8,"official":{"repos":["txh-mercury/vast"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":4,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vast-a-vision-audio-subtitle-text-omni-1#ran","syntology_url":"https://syntology.ai/paper/2305.18500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18500"}}}},{"paper":"/paper/vlab-enhancing-video-language-pre-training-by","slug":"vlab-enhancing-video-language-pre-training-by","title":"VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending","date":"2023-05-22","arxiv_id":"2305.13167","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/imagebind-one-embedding-space-to-bind-them","slug":"imagebind-one-embedding-space-to-bind-them","title":"ImageBind: One Embedding Space To Bind Them All","date":"2023-05-09","arxiv_id":"2305.05665","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":34,"samples_ran":24,"samples_constructed":14,"samples_ran_checked":21,"samples_ran_instrument_failed":3,"samples_unverified":10,"pointer_only_for_licence":32,"official":{"repos":["facebookresearch/imagebind"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":10,"n_ran_no_instrument_failure":15,"n_unverified":7,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/imagebind-one-embedding-space-to-bind-them#ran","syntology_url":"https://syntology.ai/paper/2305.05665","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.05665"}}}},{"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/valor-vision-audio-language-omni-perception","slug":"valor-vision-audio-language-omni-perception","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","date":"2023-04-17","arxiv_id":"2304.08345","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/mammut-a-simple-architecture-for-joint","slug":"mammut-a-simple-architecture-for-joint","title":"MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks","date":"2023-03-29","arxiv_id":"2303.16839","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":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mammut-a-simple-architecture-for-joint#ran","syntology_url":"https://syntology.ai/paper/2303.16839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16839"}}}},{"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":2,"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/sem-pos-grammatically-and-semantically","slug":"sem-pos-grammatically-and-semantically","title":"SEM-POS: Grammatically and Semantically Correct Video Captioning","date":"2023-03-26","arxiv_id":"2303.14829","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/video-text-as-game-players-hierarchical","slug":"video-text-as-game-players-hierarchical","title":"Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning","date":"2023-03-25","arxiv_id":"2303.14369","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":12,"samples_constructed":7,"samples_ran_checked":11,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["jpthu17/HBI"],"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":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-text-as-game-players-hierarchical#ran","syntology_url":"https://syntology.ai/paper/2303.14369","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14369"}}}},{"paper":"/paper/meltr-meta-loss-transformer-for-learning-to","slug":"meltr-meta-loss-transformer-for-learning-to","title":"MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models","date":"2023-03-23","arxiv_id":"2303.13009","rows_on_this_dataset":7,"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":0,"official":{"repos":["mlvlab/MELTR"],"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/meltr-meta-loss-transformer-for-learning-to#ran","syntology_url":"https://syntology.ai/paper/2303.13009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.13009"}}}},{"paper":"/paper/text-with-knowledge-graph-augmented","slug":"text-with-knowledge-graph-augmented","title":"Text with Knowledge Graph Augmented Transformer for Video Captioning","date":"2023-03-22","arxiv_id":"2303.12423","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/diffusionret-generative-text-video-retrieval","slug":"diffusionret-generative-text-video-retrieval","title":"DiffusionRet: Generative Text-Video Retrieval with Diffusion Model","date":"2023-03-17","arxiv_id":"2303.09867","rows_on_this_dataset":2,"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":["jpthu17/diffusionret"],"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/diffusionret-generative-text-video-retrieval#ran","syntology_url":"https://syntology.ai/paper/2303.09867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09867"}}}},{"paper":"/paper/multi-efficient-video-and-language","slug":"multi-efficient-video-and-language","title":"MuLTI: Efficient Video-and-Language Understanding with Text-Guided MultiWay-Sampler and Multiple Choice Modeling","date":"2023-03-10","arxiv_id":"2303.05707","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/vid2seq-large-scale-pretraining-of-a-visual","slug":"vid2seq-large-scale-pretraining-of-a-visual","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","date":"2023-02-27","arxiv_id":"2302.14115","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/video-text-retrieval-by-supervised-multi","slug":"video-text-retrieval-by-supervised-multi","title":"Video-Text Retrieval by Supervised Sparse Multi-Grained Learning","date":"2023-02-19","arxiv_id":"2302.09473","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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":3,"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/revisiting-temporal-modeling-for-clip-based","slug":"revisiting-temporal-modeling-for-clip-based","title":"Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring","date":"2023-01-26","arxiv_id":"2301.11116","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pidro-parallel-isomeric-attention-with","slug":"pidro-parallel-isomeric-attention-with","title":"PIDRo: Parallel Isomeric Attention with Dynamic Routing for Text-Video Retrieval","date":"2023-01-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/cap4video-what-can-auxiliary-captions-do-for","slug":"cap4video-what-can-auxiliary-captions-do-for","title":"Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?","date":"2022-12-31","arxiv_id":"2301.00184","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":25,"samples_ran":20,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":11,"samples_unverified":5,"pointer_only_for_licence":11,"official":{"repos":["whwu95/Cap4Video"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cap4video-what-can-auxiliary-captions-do-for#ran","syntology_url":"https://syntology.ai/paper/2301.00184","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00184"}}}},{"paper":"/paper/hitea-hierarchical-temporal-aware-video","slug":"hitea-hierarchical-temporal-aware-video","title":"HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training","date":"2022-12-30","arxiv_id":"2212.14546","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"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":2,"code_links":0,"syntology":null},{"paper":"/paper/vindlu-a-recipe-for-effective-video-and","slug":"vindlu-a-recipe-for-effective-video-and","title":"VindLU: A Recipe for Effective Video-and-Language Pretraining","date":"2022-12-09","arxiv_id":"2212.05051","rows_on_this_dataset":1,"code_links":1,"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":2,"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/masked-contrastive-pre-training-for-efficient","slug":"masked-contrastive-pre-training-for-efficient","title":"Masked Contrastive Pre-Training for Efficient Video-Text Retrieval","date":"2022-12-02","arxiv_id":"2212.00986","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/seeing-what-you-miss-vision-language-pre","slug":"seeing-what-you-miss-vision-language-pre","title":"Seeing What You Miss: Vision-Language Pre-training with Semantic Completion Learning","date":"2022-11-24","arxiv_id":"2211.13437","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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":1,"code_links":1,"syntology":null},{"paper":"/paper/x-2-vlm-all-in-one-pre-trained-model-for","slug":"x-2-vlm-all-in-one-pre-trained-model-for","title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks","date":"2022-11-22","arxiv_id":"2211.12402","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":6,"official":{"repos":["zengyan-97/x2-vlm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/x-2-vlm-all-in-one-pre-trained-model-for#ran","syntology_url":"https://syntology.ai/paper/2211.12402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.12402"}}}},{"paper":"/paper/expectation-maximization-contrastive-learning","slug":"expectation-maximization-contrastive-learning","title":"Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations","date":"2022-11-21","arxiv_id":"2211.11427","rows_on_this_dataset":3,"code_links":4,"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":0,"official":{"repos":["jpthu17/emcl"],"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":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/expectation-maximization-contrastive-learning#ran","syntology_url":"https://syntology.ai/paper/2211.11427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.11427"}}}},{"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":1,"code_links":0,"syntology":null},{"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/omnivl-one-foundation-model-for-image","slug":"omnivl-one-foundation-model-for-image","title":"OmniVL:One Foundation Model for Image-Language and Video-Language Tasks","date":"2022-09-15","arxiv_id":"2209.07526","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/clip-vip-adapting-pre-trained-image-text","slug":"clip-vip-adapting-pre-trained-image-text","title":"CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment","date":"2022-09-14","arxiv_id":"2209.06430","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":4,"official":{"repos":["microsoft/xpretrain"],"state":"official (archive's flag): 4 ran","n_ran":4,"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/clip-vip-adapting-pre-trained-image-text#ran","syntology_url":"https://syntology.ai/paper/2209.06430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.06430"}}}},{"paper":"/paper/an-empirical-study-of-end-to-end-video","slug":"an-empirical-study-of-end-to-end-video","title":"An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling","date":"2022-09-04","arxiv_id":"2209.01540","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/diverse-video-captioning-by-adaptive-spatio","slug":"diverse-video-captioning-by-adaptive-spatio","title":"Diverse Video Captioning by Adaptive Spatio-temporal Attention","date":"2022-08-19","arxiv_id":"2208.09266","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/clover-towards-a-unified-video-language","slug":"clover-towards-a-unified-video-language","title":"Clover: Towards A Unified Video-Language Alignment and Fusion Model","date":"2022-07-16","arxiv_id":"2207.07885","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/ts2-net-token-shift-and-selection-transformer","slug":"ts2-net-token-shift-and-selection-transformer","title":"TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval","date":"2022-07-16","arxiv_id":"2207.07852","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":4,"official":{"repos":["yuqi657/ts2_net"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ts2-net-token-shift-and-selection-transformer#ran","syntology_url":"https://syntology.ai/paper/2207.07852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.07852"}}}},{"paper":"/paper/x-clip-end-to-end-multi-grained-contrastive","slug":"x-clip-end-to-end-multi-grained-contrastive","title":"X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval","date":"2022-07-15","arxiv_id":"2207.07285","rows_on_this_dataset":1,"code_links":3,"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":1,"official":{"repos":["xuguohai/X-CLIP"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/x-clip-end-to-end-multi-grained-contrastive#ran","syntology_url":"https://syntology.ai/paper/2207.07285","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.07285"}}}},{"paper":"/paper/lat-latent-translation-with-cycle-consistency","slug":"lat-latent-translation-with-cycle-consistency","title":"LaT: Latent Translation with Cycle-Consistency for Video-Text Retrieval","date":"2022-07-11","arxiv_id":"2207.04858","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/rome-role-aware-mixture-of-expert-transformer","slug":"rome-role-aware-mixture-of-expert-transformer","title":"RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval","date":"2022-06-26","arxiv_id":"2206.12845","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/revealing-single-frame-bias-for-video-and","slug":"revealing-single-frame-bias-for-video-and","title":"Revealing Single Frame Bias for Video-and-Language Learning","date":"2022-06-07","arxiv_id":"2206.03428","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":4,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["jayleicn/singularity"],"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/revealing-single-frame-bias-for-video-and#ran","syntology_url":"https://syntology.ai/paper/2206.03428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.03428"}}}},{"paper":"/paper/git-a-generative-image-to-text-transformer","slug":"git-a-generative-image-to-text-transformer","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","date":"2022-05-27","arxiv_id":"2205.14100","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":14,"samples_ran_instrument_failed":0,"samples_unverified":7,"pointer_only_for_licence":0,"official":{"repos":["microsoft/GenerativeImage2Text"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":7,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/git-a-generative-image-to-text-transformer#ran","syntology_url":"https://syntology.ai/paper/2205.14100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14100"}}}},{"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":1,"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/centerclip-token-clustering-for-efficient","slug":"centerclip-token-clustering-for-efficient","title":"CenterCLIP: Token Clustering for Efficient Text-Video Retrieval","date":"2022-05-02","arxiv_id":"2205.00823","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":1,"official":{"repos":["mzhaoshuai/CenterCLIP"],"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/centerclip-token-clustering-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2205.00823","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.00823"}}}},{"paper":"/paper/miles-visual-bert-pre-training-with-injected","slug":"miles-visual-bert-pre-training-with-injected","title":"MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval","date":"2022-04-26","arxiv_id":"2204.12408","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cots-collaborative-two-stream-vision-language","slug":"cots-collaborative-two-stream-vision-language","title":"COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval","date":"2022-04-15","arxiv_id":"2204.07441","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/hunyuan-tvr-for-text-video-retrivial","slug":"hunyuan-tvr-for-text-video-retrivial","title":"Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations","date":"2022-04-07","arxiv_id":"2204.03382","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/learning-audio-video-modalities-from-image","slug":"learning-audio-video-modalities-from-image","title":"Learning Audio-Video Modalities from Image Captions","date":"2022-04-01","arxiv_id":"2204.00679","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/socratic-models-composing-zero-shot","slug":"socratic-models-composing-zero-shot","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","date":"2022-04-01","arxiv_id":"2204.00598","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/x-pool-cross-modal-language-video-attention","slug":"x-pool-cross-modal-language-video-attention","title":"X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval","date":"2022-03-28","arxiv_id":"2203.15086","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":2,"official":{"repos":["layer6ai-labs/xpool"],"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/x-pool-cross-modal-language-video-attention#ran","syntology_url":"https://syntology.ai/paper/2203.15086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15086"}}}},{"paper":"/paper/all-in-one-exploring-unified-video-language","slug":"all-in-one-exploring-unified-video-language","title":"All in One: Exploring Unified Video-Language Pre-training","date":"2022-03-14","arxiv_id":"2203.07303","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/disentangled-representation-learning-for-text","slug":"disentangled-representation-learning-for-text","title":"Disentangled Representation Learning for Text-Video Retrieval","date":"2022-03-14","arxiv_id":"2203.07111","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":5,"samples_unverified":2,"pointer_only_for_licence":4,"official":{"repos":["foolwood/DRL"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/disentangled-representation-learning-for-text#ran","syntology_url":"https://syntology.ai/paper/2203.07111","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.07111"}}}},{"paper":"/paper/mdmmt-2-multidomain-multimodal-transformer","slug":"mdmmt-2-multidomain-multimodal-transformer","title":"MDMMT-2: Multidomain Multimodal Transformer for Video Retrieval, One More Step Towards Generalization","date":"2022-03-14","arxiv_id":"2203.07086","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/end-to-end-generative-pretraining-for","slug":"end-to-end-generative-pretraining-for","title":"End-to-end Generative Pretraining for Multimodal Video Captioning","date":"2022-01-20","arxiv_id":"2201.08264","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/bridgeformer-bridging-video-text-retrieval","slug":"bridgeformer-bridging-video-text-retrieval","title":"Bridging Video-text Retrieval with Multiple Choice Questions","date":"2022-01-13","arxiv_id":"2201.04850","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":24,"samples_ran":13,"samples_constructed":8,"samples_ran_checked":9,"samples_ran_instrument_failed":4,"samples_unverified":11,"pointer_only_for_licence":6,"official":{"repos":["tencentarc/mcq"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bridgeformer-bridging-video-text-retrieval#ran","syntology_url":"https://syntology.ai/paper/2201.04850","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.04850"}}}},{"paper":"/paper/cross-modal-retrieval-with-querybank","slug":"cross-modal-retrieval-with-querybank","title":"Cross Modal Retrieval with Querybank Normalisation","date":"2021-12-23","arxiv_id":"2112.12777","rows_on_this_dataset":1,"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":1,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["ioanacroi/qb-norm"],"state":"official (archive's flag): 2 ran","n_ran":2,"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/cross-modal-retrieval-with-querybank#ran","syntology_url":"https://syntology.ai/paper/2112.12777","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.12777"}}}},{"paper":"/paper/align-and-prompt-video-and-language-pre","slug":"align-and-prompt-video-and-language-pre","title":"Align and Prompt: Video-and-Language Pre-training with Entity Prompts","date":"2021-12-17","arxiv_id":"2112.09583","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/lightweight-attentional-feature-fusion-for","slug":"lightweight-attentional-feature-fusion-for","title":"Lightweight Attentional Feature Fusion: A New Baseline for Text-to-Video Retrieval","date":"2021-12-03","arxiv_id":"2112.01832","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/object-aware-video-language-pre-training-for","slug":"object-aware-video-language-pre-training-for","title":"Object-aware Video-language Pre-training for Retrieval","date":"2021-12-01","arxiv_id":"2112.00656","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/clip-meets-video-captioners-attribute-aware","slug":"clip-meets-video-captioners-attribute-aware","title":"CLIP Meets Video Captioning: Concept-Aware Representation Learning Does Matter","date":"2021-11-30","arxiv_id":"2111.15162","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/nuwa-visual-synthesis-pre-training-for-neural","slug":"nuwa-visual-synthesis-pre-training-for-neural","title":"NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion","date":"2021-11-24","arxiv_id":"2111.12417","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":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/nuwa-visual-synthesis-pre-training-for-neural#ran","syntology_url":"https://syntology.ai/paper/2111.12417","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.12417"}}}},{"paper":"/paper/violet-end-to-end-video-language-transformers","slug":"violet-end-to-end-video-language-transformers","title":"VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling","date":"2021-11-24","arxiv_id":"2111.12681","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":2,"official":{"repos":["tsujuifu/pytorch_violet"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/violet-end-to-end-video-language-transformers#ran","syntology_url":"https://syntology.ai/paper/2111.12681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.12681"}}}},{"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/advancing-high-resolution-video-language","slug":"advancing-high-resolution-video-language","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","date":"2021-11-19","arxiv_id":"2111.10337","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/clip2tv-an-empirical-study-on-transformer","slug":"clip2tv-an-empirical-study-on-transformer","title":"CLIP2TV: Align, Match and Distill for Video-Text Retrieval","date":"2021-11-10","arxiv_id":"2111.05610","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/video-and-text-matching-with-conditioned","slug":"video-and-text-matching-with-conditioned","title":"Video and Text Matching with Conditioned Embeddings","date":"2021-10-21","arxiv_id":"2110.11298","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/videoclip-contrastive-pre-training-for-zero","slug":"videoclip-contrastive-pre-training-for-zero","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","date":"2021-09-28","arxiv_id":"2109.14084","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/improving-video-text-retrieval-by-multi","slug":"improving-video-text-retrieval-by-multi","title":"Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss","date":"2021-09-09","arxiv_id":"2109.04290","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/taco-token-aware-cascade-contrastive-learning","slug":"taco-token-aware-cascade-contrastive-learning","title":"TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment","date":"2021-08-23","arxiv_id":"2108.09980","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/clip2video-mastering-video-text-retrieval-via","slug":"clip2video-mastering-video-text-retrieval-via","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","date":"2021-06-21","arxiv_id":"2106.11097","rows_on_this_dataset":2,"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":["CryhanFang/CLIP2Video"],"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/clip2video-mastering-video-text-retrieval-via#ran","syntology_url":"https://syntology.ai/paper/2106.11097","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11097"}}}},{"paper":"/paper/vlm-task-agnostic-video-language-model-pre","slug":"vlm-task-agnostic-video-language-model-pre","title":"VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding","date":"2021-05-20","arxiv_id":"2105.09996","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/godiva-generating-open-domain-videos-from","slug":"godiva-generating-open-domain-videos-from","title":"GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions","date":"2021-04-30","arxiv_id":"2104.14806","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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/clip4clip-an-empirical-study-of-clip-for-end","slug":"clip4clip-an-empirical-study-of-clip-for-end","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","date":"2021-04-18","arxiv_id":"2104.08860","rows_on_this_dataset":4,"code_links":5,"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":3,"official":{"repos":["ArrowLuo/CLIP4Clip"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/clip4clip-an-empirical-study-of-clip-for-end#ran","syntology_url":"https://syntology.ai/paper/2104.08860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08860"}}}},{"paper":"/paper/frozen-in-time-a-joint-video-and-image","slug":"frozen-in-time-a-joint-video-and-image","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","date":"2021-04-01","arxiv_id":"2104.00650","rows_on_this_dataset":3,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["m-bain/frozen-in-time"],"state":"official (archive's flag): 10 ran","n_ran":10,"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/frozen-in-time-a-joint-video-and-image#ran","syntology_url":"https://syntology.ai/paper/2104.00650","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00650"}}}},{"paper":"/paper/mdmmt-multidomain-multimodal-transformer-for","slug":"mdmmt-multidomain-multimodal-transformer-for","title":"MDMMT: Multidomain Multimodal Transformer for Video Retrieval","date":"2021-03-19","arxiv_id":"2103.10699","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":4,"samples_unverified":1,"pointer_only_for_licence":5,"official":{"repos":["papermsucode/mdmmt"],"state":"official (archive's flag): 4 ran","n_ran":4,"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/mdmmt-multidomain-multimodal-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2103.10699","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.10699"}}}},{"paper":"/paper/a-straightforward-framework-for-video","slug":"a-straightforward-framework-for-video","title":"A Straightforward Framework For Video Retrieval Using CLIP","date":"2021-02-24","arxiv_id":"2102.12443","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/multi-modal-transformer-for-video-retrieval","slug":"multi-modal-transformer-for-video-retrieval","title":"Multi-modal Transformer for Video Retrieval","date":"2020-07-21","arxiv_id":"2007.10639","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":6,"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/multi-modal-transformer-for-video-retrieval#ran","syntology_url":"https://syntology.ai/paper/2007.10639","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.10639"}}}},{"paper":"/paper/noise-estimation-using-density-estimation-for","slug":"noise-estimation-using-density-estimation-for","title":"Noise Estimation Using Density Estimation for Self-Supervised Multimodal Learning","date":"2020-03-06","arxiv_id":"2003.03186","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/univilm-a-unified-video-and-language-pre","slug":"univilm-a-unified-video-and-language-pre","title":"UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation","date":"2020-02-15","arxiv_id":"2002.06353","rows_on_this_dataset":1,"code_links":2,"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":1,"official":{"repos":["microsoft/UniVL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/univilm-a-unified-video-and-language-pre#ran","syntology_url":"https://syntology.ai/paper/2002.06353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.06353"}}}},{"paper":"/paper/end-to-end-learning-of-visual-representations","slug":"end-to-end-learning-of-visual-representations","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","date":"2019-12-13","arxiv_id":"1912.06430","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":4,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["antoine77340/MIL-NCE_HowTo100M"],"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/end-to-end-learning-of-visual-representations#ran","syntology_url":"https://syntology.ai/paper/1912.06430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.06430"}}}},{"paper":"/paper/use-what-you-have-video-retrieval-using","slug":"use-what-you-have-video-retrieval-using","title":"Use What You Have: Video Retrieval Using Representations From Collaborative Experts","date":"2019-07-31","arxiv_id":"1907.13487","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/use-what-you-have-video-retrieval-using#ran","syntology_url":"https://syntology.ai/paper/1907.13487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.13487"}}}},{"paper":"/paper/howto100m-learning-a-text-video-embedding-by","slug":"howto100m-learning-a-text-video-embedding-by","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","date":"2019-06-07","arxiv_id":"1906.03327","rows_on_this_dataset":3,"code_links":4,"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":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/howto100m-learning-a-text-video-embedding-by#ran","syntology_url":"https://syntology.ai/paper/1906.03327","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.03327"}}}},{"paper":"/paper/a-joint-sequence-fusion-model-for-video","slug":"a-joint-sequence-fusion-model-for-video","title":"A Joint Sequence Fusion Model for Video Question Answering and Retrieval","date":"2018-08-07","arxiv_id":"1808.02559","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":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-joint-sequence-fusion-model-for-video#ran","syntology_url":"https://syntology.ai/paper/1808.02559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.02559"}}}},{"paper":"/paper/learning-joint-embedding-with-multimodal-cues","slug":"learning-joint-embedding-with-multimodal-cues","title":"Learning Joint Embedding with Multimodal Cues for Cross-Modal Video-Text Retrieval","date":"2018-06-11","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/temporal-tessellation-a-unified-approach-for","slug":"temporal-tessellation-a-unified-approach-for","title":"Temporal Tessellation: A Unified Approach for Video Analysis","date":"2016-12-21","arxiv_id":"1612.06950","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-language-visual-embedding-for-movie","slug":"learning-language-visual-embedding-for-movie","title":"Learning Language-Visual Embedding for Movie Understanding with Natural-Language","date":"2016-09-26","arxiv_id":"1609.08124","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"papers_where_code_ran":49,"papers_where_code_ran_first_page":"/dataset/msr-vtt/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":2,"url":"/dataset/msr-vtt/papers/2","json":"/dataset/msr-vtt/papers/2.json","rows":17},{"order":"ran","page":1,"of":1,"url":"/dataset/msr-vtt/papers/ran/1","json":"/dataset/msr-vtt/papers/ran/1.json","rows":49}],"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":52,"samples_harvested":514,"samples_ran":389,"samples_constructed":59,"samples_ran_checked":271,"samples_ran_instrument_failed":118,"samples_unverified":125,"pointer_only_for_licence":170,"papers_with_no_sample_that_ran":3,"papers_with_a_sample_that_ran":49,"papers_with_a_run_with_no_instrument_failure":39,"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":3,"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/video-retrieval-on-msr-vtt-1ka","since_archive":"/sota/video-retrieval-on-msr-vtt-1ka#since-judged","papers_judged":2,"placed":0},{"leaderboard":"/sota/zero-shot-video-retrieval-on-msr-vtt","since_archive":"/sota/zero-shot-video-retrieval-on-msr-vtt#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":"7739e9e8dc6ef7881b4f447055c356259b4b8f8fde78a4e163f59cf35e050d0f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}