{"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":"/task/zero-shot-video-retrieval","name":"Zero-Shot Video Retrieval","slug":"zero-shot-video-retrieval","description_markdown":"Zero-shot video retrieval is the task of retrieving relevant videos based on a query (usually in text form) without any prior training on specific examples of those videos. Unlike traditional retrieval methods that rely on supervised learning with annotated datasets, zero-shot retrieval leverages pre-trained models, typically based on large-scale vision-language learning, to understand semantic relationships between textual descriptions and video content.\r\n\r\nThis approach enables retrieval of unseen video concepts by generalizing knowledge from diverse training data, making it highly useful for domains with limited labeled data, such as broadcast media, surveillance, and historical archives.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":40,"papers_with_code":33,"benchmarks":8,"benchmark_tables_in_archive":8,"benchmark_tables_shown":8,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":7,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/zero-shot-video-retrieval-on-msr-vtt","slug":"zero-shot-video-retrieval-on-msr-vtt","dataset":"MSR-VTT","dataset_url":"/dataset/msr-vtt","rows_in_archive":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_title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","paper_url":"/paper/internvideo2-scaling-video-foundation-models","paper_date":"2024-03-22","arxiv_id":"2403.15377","code_links":[{"title":"opengvlab/internvideo","url":"https://github.com/opengvlab/internvideo"},{"title":"opengvlab/internvideo2","url":"https://github.com/opengvlab/internvideo2"}],"syntology":null}},{"leaderboard":"/sota/zero-shot-video-retrieval-on-didemo","slug":"zero-shot-video-retrieval-on-didemo","dataset":"DiDeMo","dataset_url":"/dataset/didemo","rows_in_archive":26,"metrics":["text-to-video R@1","text-to-video R@5","text-to-video R@10","video-to-text R@1","video-to-text R@5","video-to-text R@10","text-to-video Median Rank","video-to-text Median Rank"],"first_row_in_archive_order":{"model":"InternVideo2-6B","paper_title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","paper_url":"/paper/internvideo2-scaling-video-foundation-models","paper_date":"2024-03-22","arxiv_id":"2403.15377","code_links":[{"title":"opengvlab/internvideo","url":"https://github.com/opengvlab/internvideo"},{"title":"opengvlab/internvideo2","url":"https://github.com/opengvlab/internvideo2"}],"syntology":null}},{"leaderboard":"/sota/zero-shot-video-retrieval-on-lsmdc","slug":"zero-shot-video-retrieval-on-lsmdc","dataset":"LSMDC","dataset_url":"/dataset/lsmdc","rows_in_archive":16,"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"],"first_row_in_archive_order":{"model":"InternVideo2-6B","paper_title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","paper_url":"/paper/internvideo2-scaling-video-foundation-models","paper_date":"2024-03-22","arxiv_id":"2403.15377","code_links":[{"title":"opengvlab/internvideo","url":"https://github.com/opengvlab/internvideo"},{"title":"opengvlab/internvideo2","url":"https://github.com/opengvlab/internvideo2"}],"syntology":null}},{"leaderboard":"/sota/zero-shot-video-retrieval-on-msvd","slug":"zero-shot-video-retrieval-on-msvd","dataset":"MSVD","dataset_url":"/dataset/msvd","rows_in_archive":14,"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_title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","paper_url":"/paper/internvideo2-scaling-video-foundation-models","paper_date":"2024-03-22","arxiv_id":"2403.15377","code_links":[{"title":"opengvlab/internvideo","url":"https://github.com/opengvlab/internvideo"},{"title":"opengvlab/internvideo2","url":"https://github.com/opengvlab/internvideo2"}],"syntology":null}},{"leaderboard":"/sota/zero-shot-video-retrieval-on-activitynet","slug":"zero-shot-video-retrieval-on-activitynet","dataset":"ActivityNet","dataset_url":"/dataset/activitynet","rows_in_archive":12,"metrics":["text-to-video R@1","text-to-video R@5","text-to-video R@10","video-to-text R@1","video-to-text R@5","video-to-text R@10"],"first_row_in_archive_order":{"model":"InternVideo2-6B","paper_title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","paper_url":"/paper/internvideo2-scaling-video-foundation-models","paper_date":"2024-03-22","arxiv_id":"2403.15377","code_links":[{"title":"opengvlab/internvideo","url":"https://github.com/opengvlab/internvideo"},{"title":"opengvlab/internvideo2","url":"https://github.com/opengvlab/internvideo2"}],"syntology":null}},{"leaderboard":"/sota/zero-shot-video-retrieval-on-youcook2","slug":"zero-shot-video-retrieval-on-youcook2","dataset":"YouCook2","dataset_url":"/dataset/youcook2","rows_in_archive":9,"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"],"first_row_in_archive_order":{"model":"OmniVec2","paper_title":"OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","paper_url":"/paper/omnivec2-a-novel-transformer-based-network","paper_date":"2024-01-01","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/zero-shot-video-retrieval-on-vatex","slug":"zero-shot-video-retrieval-on-vatex","dataset":"VATEX","dataset_url":"/dataset/vatex","rows_in_archive":5,"metrics":["text-to-video R@1","text-to-video R@5","text-to-video R@10","video-to-text R@1","video-to-text R@5","video-to-text R@10"],"first_row_in_archive_order":{"model":"GRAM","paper_title":"Gramian Multimodal Representation Learning and Alignment","paper_url":"/paper/gramian-multimodal-representation-learning","paper_date":"2024-12-16","arxiv_id":"2412.11959","code_links":[{"title":"ispamm/GRAM","url":"https://github.com/ispamm/GRAM"},{"title":"luigisigillo/gwit","url":"https://github.com/luigisigillo/gwit"}],"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":5,"n_honours":3,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","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"}},"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"]}}}},{"leaderboard":"/sota/zero-shot-video-retrieval-on-msr-vtt-full","slug":"zero-shot-video-retrieval-on-msr-vtt-full","dataset":"MSR-VTT-full","dataset_url":null,"rows_in_archive":3,"metrics":["text-to-video R@1","text-to-video R@5","text-to-video R@10","video-to-text R@1","video-to-text R@5","video-to-text R@10"],"first_row_in_archive_order":{"model":"InternVL-G","paper_title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","paper_url":"/paper/internvl-scaling-up-vision-foundation-models","paper_date":"2023-12-21","arxiv_id":"2312.14238","code_links":[{"title":"opengvlab/internvl","url":"https://github.com/opengvlab/internvl"},{"title":"opengvlab/internvl-mmdetseg","url":"https://github.com/opengvlab/internvl-mmdetseg"}],"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/internvl-scaling-up-vision-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2312.14238","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14238"}},"official":{"repos":["opengvlab/internvl"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}}],"datasets":[{"url":"/dataset/activitynet","name":"ActivityNet","full_name":"","num_papers_in_archive":807},{"url":"/dataset/msr-vtt","name":"MSR-VTT","full_name":"","num_papers_in_archive":640},{"url":"/dataset/msvd","name":"MSVD","full_name":"Microsoft Research Video Description Corpus","num_papers_in_archive":327},{"url":"/dataset/didemo","name":"DiDeMo","full_name":"Distinct Describable Moments","num_papers_in_archive":216},{"url":"/dataset/youcook2","name":"YouCook2","full_name":"","num_papers_in_archive":198},{"url":"/dataset/lsmdc","name":"LSMDC","full_name":"Large Scale Movie Description Challenge","num_papers_in_archive":126},{"url":"/dataset/vatex","name":"VATEX","full_name":"Video And TEXt","num_papers_in_archive":118}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":40,"of":40,"of_with_code":33,"tagged_in_all":40,"counts":{"archive_papers_tagged":40,"with_a_code_link":33,"where_syntology_ran_a_sample":19,"not_listed_spam_title":0,"listed":40,"listed_where_code_ran":19,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":16,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":16,"listed_every_run_a_failure_of_syntologys_instrument":3,"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 the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/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","repositories_listed":6,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":4,"n_honours":3,"n_violates":0,"n_no_contract":6,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":5,"syntology":{"n":8,"n_ran":5,"n_constructed":4,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":5,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":5,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":4,"syntology":{"n":19,"n_ran":17,"n_constructed":0,"n_ran_checked":8,"n_instrument":9,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":2,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 9 where Syntology's instrument failed) · 2 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":4,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":3,"syntology":{"n":34,"n_ran":24,"n_constructed":14,"n_ran_checked":21,"n_instrument":3,"n_unverified":10,"n_honours":1,"n_violates":1,"n_no_contract":19,"n_pointer_only":32,"phrase":"24 ran (of which 14 constructed an object rather than computing a result; 21 with no instrument failure: 1 honoured, 1 violated, 19 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":2,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":5,"n_honours":3,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":2,"syntology":null},{"url":"/paper/internvl-scaling-up-vision-foundation-models","slug":"internvl-scaling-up-vision-foundation-models","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","date":"2023-12-21","arxiv_id":"2312.14238","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/internvl-scaling-up-vision-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2312.14238","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14238"}},"official":{"repos":["opengvlab/internvl"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/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","repositories_listed":2,"syntology":{"n":42,"n_ran":35,"n_constructed":4,"n_ran_checked":25,"n_instrument":10,"n_unverified":7,"n_honours":4,"n_violates":1,"n_no_contract":20,"n_pointer_only":8,"phrase":"35 ran (of which 4 constructed an object rather than computing a result; 25 with no instrument failure: 4 honoured, 1 violated, 20 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":2,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":2,"syntology":{"n":24,"n_ran":13,"n_constructed":8,"n_ran_checked":9,"n_instrument":4,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":6,"phrase":"13 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 11 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":2,"syntology":null},{"url":"/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","repositories_listed":2,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":17,"n_ran":17,"n_constructed":0,"n_ran_checked":17,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":14,"n_pointer_only":6,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 3 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/everything-at-once-multi-modal-fusion-1","slug":"everything-at-once-multi-modal-fusion-1","title":"Everything at Once - Multi-Modal Fusion Transformer for Video Retrieval","date":"2022-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/everything-at-once-multi-modal-fusion","slug":"everything-at-once-multi-modal-fusion","title":"Everything at Once -- Multi-modal Fusion Transformer for Video Retrieval","date":"2021-12-08","arxiv_id":"2112.04446","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","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"}},"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":[]}}},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","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"}},"official":null}},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/omnivec2-a-novel-transformer-based-network","slug":"omnivec2-a-novel-transformer-based-network","title":"OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/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","repositories_listed":0,"syntology":null},{"url":"/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","repositories_listed":0,"syntology":null},{"url":"/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","repositories_listed":0,"syntology":null},{"url":"/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","repositories_listed":0,"syntology":null},{"url":"/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","repositories_listed":0,"syntology":null},{"url":"/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","repositories_listed":0,"syntology":null}],"syntology_records":20,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_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'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/zero-shot-video-retrieval-on-msr-vtt","since_archive":"/sota/zero-shot-video-retrieval-on-msr-vtt#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/zero-shot-video-retrieval-on-didemo","since_archive":"/sota/zero-shot-video-retrieval-on-didemo#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/zero-shot-video-retrieval-on-activitynet","since_archive":"/sota/zero-shot-video-retrieval-on-activitynet#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":19,"papers_where_code_ran_first_page":"/task/zero-shot-video-retrieval/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/zero-shot-video-retrieval/papers/ran/1","json":"/task/zero-shot-video-retrieval/papers/ran/1.json","rows":19}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper 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"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"d1baf66a19febf422bf2bdb5f11bd7d5631894d0c0457b8db86ad15f45fa0301","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}