{"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/papers/2","list_of":"/dataset/msr-vtt","dataset":"MSR-VTT","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","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)"},"order":"archive","order_definition":"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":2,"pages_in_order":2,"rows_per_page":100,"rows":[101,117],"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":42,"every_run_a_failure_of_syntologys_instrument":7,"listed_with_a_run_with_no_instrument_failure":42,"listed_every_run_a_failure_of_syntologys_instrument":7,"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"},"first_page":"/dataset/msr-vtt","prev":"/dataset/msr-vtt","next":null,"papers":[{"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":"2026-09-28T10:30:06+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":"2026-09-28T10:30:06+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":"2026-09-28T10:30:06+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":"2026-09-28T10:30:06+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":"2026-09-28T10:30:06+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":"2026-09-28T10:30:06+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":"2026-09-28T10:30:06+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":2,"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":"2026-09-28T10:30:06+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":"2026-09-28T10:30:06+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":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":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}],"record_sha256":"c86d8a8dac1327097f18823debd698969557c1218cac73ef4b75fd02cf3c3ad1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}