{"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/video-retrieval","name":"Video Retrieval","slug":"video-retrieval","description_markdown":"The objective of video retrieval is as follows: given a text query and a pool of candidate videos, select the video which corresponds to the text query.  Typically, the videos are returned as a ranked list of candidates and scored via document retrieval metrics.","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":486,"papers_with_code":255,"benchmarks":19,"benchmark_tables_in_archive":19,"benchmark_tables_shown":19,"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":35,"subtasks":5,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/video-retrieval-on-msr-vtt-1ka","slug":"video-retrieval-on-msr-vtt-1ka","dataset":"MSR-VTT-1kA","dataset_url":"/dataset/msr-vtt","rows_in_archive":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_title":"Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations","paper_url":"/paper/hunyuan-tvr-for-text-video-retrivial","paper_date":"2022-04-07","arxiv_id":"2204.03382","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-retrieval-on-didemo","slug":"video-retrieval-on-didemo","dataset":"DiDeMo","dataset_url":"/dataset/didemo","rows_in_archive":40,"metrics":["text-to-video R@1","text-to-video R@5","text-to-video R@10","text-to-video R@50","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","text-to-videoR@1"],"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/video-retrieval-on-msr-vtt","slug":"video-retrieval-on-msr-vtt","dataset":"MSR-VTT","dataset_url":"/dataset/msr-vtt","rows_in_archive":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_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/video-retrieval-on-lsmdc","slug":"video-retrieval-on-lsmdc","dataset":"LSMDC","dataset_url":"/dataset/lsmdc","rows_in_archive":38,"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@10","video-to-text R@5","video-to-text Median Rank","video-to-text Mean 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/video-retrieval-on-activitynet","slug":"video-retrieval-on-activitynet","dataset":"ActivityNet","dataset_url":"/dataset/activitynet","rows_in_archive":31,"metrics":["text-to-video R@1","text-to-video R@5","text-to-video R@10","text-to-video R@50","text-to-video Mean Rank","text-to-video Median Rank","video-to-text R@1","video-to-text R@5","video-to-text Mean Rank","video-to-text Median Rank","video-to-text R@10","video-to-text R@50"],"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/video-retrieval-on-msvd","slug":"video-retrieval-on-msvd","dataset":"MSVD","dataset_url":"/dataset/msvd","rows_in_archive":24,"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","text-to-video R@50","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":"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/video-retrieval-on-fivr-200k","slug":"video-retrieval-on-fivr-200k","dataset":"FIVR-200K","dataset_url":"/dataset/fivr-200k","rows_in_archive":17,"metrics":["mAP (ISVR)","mAP (CSVR)","mAP (DSVR)"],"first_row_in_archive_order":{"model":"S2VS","paper_title":"Self-Supervised Video Similarity Learning","paper_url":"/paper/self-supervised-video-similarity-learning","paper_date":"2023-04-06","arxiv_id":"2304.03378","code_links":[{"title":"gkordo/s2vs","url":"https://github.com/gkordo/s2vs"}],"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"5 ran (of which 0 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) · 1 unverified","sample_list":"/paper/self-supervised-video-similarity-learning#ran","syntology_url":"https://syntology.ai/paper/2304.03378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.03378"}},"official":{"repos":["gkordo/s2vs"],"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"]}}}},{"leaderboard":"/sota/video-retrieval-on-youcook2","slug":"video-retrieval-on-youcook2","dataset":"YouCook2","dataset_url":"/dataset/youcook2","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"],"first_row_in_archive_order":{"model":"VAST","paper_title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","paper_url":"/paper/vast-a-vision-audio-subtitle-text-omni-1","paper_date":"2023-05-29","arxiv_id":"2305.18500","code_links":[{"title":"TXH-mercury/VALOR","url":"https://github.com/TXH-mercury/VALOR"},{"title":"txh-mercury/vast","url":"https://github.com/txh-mercury/vast"}],"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"]}}}},{"leaderboard":"/sota/video-retrieval-on-vatex","slug":"video-retrieval-on-vatex","dataset":"VATEX","dataset_url":"/dataset/vatex","rows_in_archive":13,"metrics":["text-to-video R@1","text-to-video R@5","text-to-video R@10","text-to-video R@50","text-to-video MedianR","text-to-video MeanR","video-to-text R@1","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/video-retrieval-on-queryd","slug":"video-retrieval-on-queryd","dataset":"QuerYD","dataset_url":"/dataset/queryd","rows_in_archive":5,"metrics":["text-to-video R@1","text-to-video R@5","text-to-video R@10"],"first_row_in_archive_order":{"model":"TESTA (ViT-B/16)","paper_title":"TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding","paper_url":"/paper/testa-temporal-spatial-token-aggregation-for","paper_date":"2023-10-29","arxiv_id":"2310.19060","code_links":[{"title":"renshuhuai-andy/testa","url":"https://github.com/renshuhuai-andy/testa"}],"syntology":{"n":15,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":4,"n_honours":3,"n_violates":0,"n_no_contract":6,"n_pointer_only":5,"phrase":"11 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; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/testa-temporal-spatial-token-aggregation-for#ran","syntology_url":"https://syntology.ai/paper/2310.19060","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.19060"}},"official":{"repos":["renshuhuai-andy/testa"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/video-retrieval-on-ssv2-label-retrieval","slug":"video-retrieval-on-ssv2-label-retrieval","dataset":"SSv2-label retrieval","dataset_url":null,"rows_in_archive":5,"metrics":["text-to-video R@1","text-to-video R@5","text-to-video R@10"],"first_row_in_archive_order":{"model":"UMT-L (ViT-L/16)","paper_title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","paper_url":"/paper/unmasked-teacher-towards-training-efficient","paper_date":"2023-03-28","arxiv_id":"2303.16058","code_links":[{"title":"opengvlab/unmasked_teacher","url":"https://github.com/opengvlab/unmasked_teacher"}],"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"]}}}},{"leaderboard":"/sota/video-retrieval-on-ssv2-template-retrieval","slug":"video-retrieval-on-ssv2-template-retrieval","dataset":"SSv2-template retrieval","dataset_url":null,"rows_in_archive":5,"metrics":["text-to-video R@1","text-to-video R@10","text-to-video R@5"],"first_row_in_archive_order":{"model":"UMT-L (ViT-L/16)","paper_title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","paper_url":"/paper/unmasked-teacher-towards-training-efficient","paper_date":"2023-03-28","arxiv_id":"2303.16058","code_links":[{"title":"opengvlab/unmasked_teacher","url":"https://github.com/opengvlab/unmasked_teacher"}],"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"]}}}},{"leaderboard":"/sota/video-retrieval-on-condensed-movies","slug":"video-retrieval-on-condensed-movies","dataset":"Condensed Movies","dataset_url":"/dataset/condensed-movies","rows_in_archive":3,"metrics":["text-to-video R@1","text-to-video R@5","text-to-video R@10"],"first_row_in_archive_order":{"model":"TESTA (ViT-B/16)","paper_title":"TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding","paper_url":"/paper/testa-temporal-spatial-token-aggregation-for","paper_date":"2023-10-29","arxiv_id":"2310.19060","code_links":[{"title":"renshuhuai-andy/testa","url":"https://github.com/renshuhuai-andy/testa"}],"syntology":{"n":15,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":4,"n_honours":3,"n_violates":0,"n_no_contract":6,"n_pointer_only":5,"phrase":"11 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; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/testa-temporal-spatial-token-aggregation-for#ran","syntology_url":"https://syntology.ai/paper/2310.19060","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.19060"}},"official":{"repos":["renshuhuai-andy/testa"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/video-retrieval-on-egoexolearn","slug":"video-retrieval-on-egoexolearn","dataset":"EgoExoLearn","dataset_url":"/dataset/egoexolearn","rows_in_archive":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"cross-view association baseline (gaze, val)","paper_title":"EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World","paper_url":"/paper/egoexolearn-a-dataset-for-bridging","paper_date":"2024-03-24","arxiv_id":"2403.16182","code_links":[{"title":"opengvlab/egoexolearn","url":"https://github.com/opengvlab/egoexolearn"}],"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/egoexolearn-a-dataset-for-bridging#ran","syntology_url":"https://syntology.ai/paper/2403.16182","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16182"}},"official":{"repos":["opengvlab/egoexolearn"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/video-retrieval-on-tgif","slug":"video-retrieval-on-tgif","dataset":"TGIF","dataset_url":"/dataset/tgif","rows_in_archive":2,"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":"MDMMT-2","paper_title":"MDMMT-2: Multidomain Multimodal Transformer for Video Retrieval, One More Step Towards Generalization","paper_url":"/paper/mdmmt-2-multidomain-multimodal-transformer","paper_date":"2022-03-14","arxiv_id":"2203.07086","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-retrieval-on-tvr","slug":"video-retrieval-on-tvr","dataset":"TVR","dataset_url":"/dataset/tvr","rows_in_archive":2,"metrics":["R@10","R@1","R@100"],"first_row_in_archive_order":{"model":"Hero w/ pre-training","paper_title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","paper_url":"/paper/hero-hierarchical-encoder-for-video-language","paper_date":"2020-05-01","arxiv_id":"2005.00200","code_links":[{"title":"linjieli222/HERO","url":"https://github.com/linjieli222/HERO"},{"title":"linjieli222/hero_video_feature_extractor","url":"https://github.com/linjieli222/hero_video_feature_extractor"},{"title":"grounded-sport-convai/goal-baselines","url":"https://gitlab.com/grounded-sport-convai/goal-baselines"}],"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hero-hierarchical-encoder-for-video-language#ran","syntology_url":"https://syntology.ai/paper/2005.00200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00200"}},"official":{"repos":["linjieli222/HERO"],"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":["listed","official"]}}}},{"leaderboard":"/sota/video-retrieval-on-charades-sta","slug":"video-retrieval-on-charades-sta","dataset":"Charades-STA","dataset_url":"/dataset/charades-sta","rows_in_archive":1,"metrics":["text-to-video Mean Rank","text-to-video Median Rank","text-to-video R@1","text-to-video R@10","video-to-text Mean Rank","video-to-text Median Rank","video-to-text R@1","video-to-text R@10"],"first_row_in_archive_order":{"model":"PO Loss","paper_title":"Rudder: A Cross Lingual Video and Text Retrieval Dataset","paper_url":"/paper/rudder-a-cross-lingual-video-and-text","paper_date":"2021-03-09","arxiv_id":"2103.05457","code_links":[{"title":"nshubham655/RUDDER","url":"https://github.com/nshubham655/RUDDER"}],"syntology":null}},{"leaderboard":"/sota/video-retrieval-on-msvd-indonesian","slug":"video-retrieval-on-msvd-indonesian","dataset":"MSVD-Indonesian","dataset_url":"/dataset/msvd-indonesian","rows_in_archive":1,"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":"X-CLIP (Cross-Lingual)","paper_title":"MSVD-Indonesian: A Benchmark for Multimodal Video-Text Tasks in Indonesian","paper_url":"/paper/msvd-indonesian-a-benchmark-for-multimodal","paper_date":"2023-06-20","arxiv_id":"2306.11341","code_links":[{"title":"willyfh/msvd-indonesian","url":"https://github.com/willyfh/msvd-indonesian"}],"syntology":null}},{"leaderboard":"/sota/video-retrieval-on-rudder","slug":"video-retrieval-on-rudder","dataset":"RUDDER","dataset_url":null,"rows_in_archive":1,"metrics":["text-to-video Mean Rank","text-to-video Median Rank","text-to-video R@1","text-to-video R@10","text-to-video R@5","text-to-video R@50","video-to-text Mean Rank","video-to-text Median Rank","video-to-text R@1","video-to-text R@10","video-to-text R@5"],"first_row_in_archive_order":{"model":"PO Loss","paper_title":"Rudder: A Cross Lingual Video and Text Retrieval Dataset","paper_url":"/paper/rudder-a-cross-lingual-video-and-text","paper_date":"2021-03-09","arxiv_id":"2103.05457","code_links":[{"title":"nshubham655/RUDDER","url":"https://github.com/nshubham655/RUDDER"}],"syntology":null}}],"datasets":[{"url":"/dataset/kinetics","name":"Kinetics","full_name":"Kinetics Human Action Video Dataset","num_papers_in_archive":1341},{"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/howto100m","name":"HowTo100M","full_name":"HowTo100M","num_papers_in_archive":286},{"url":"/dataset/webvid","name":"WebVid","full_name":"","num_papers_in_archive":257},{"url":"/dataset/charades-sta","name":"Charades-STA","full_name":"","num_papers_in_archive":236},{"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},{"url":"/dataset/tgif","name":"TGIF","full_name":"Tumblr GIF","num_papers_in_archive":51},{"url":"/dataset/tvr","name":"TVR","full_name":"TV show Retrieval","num_papers_in_archive":34},{"url":"/dataset/how2qa","name":"How2QA","full_name":"How2QA","num_papers_in_archive":28},{"url":"/dataset/cmd","name":"CMD","full_name":"Condensed Movies Dataset","num_papers_in_archive":19},{"url":"/dataset/violin","name":"Violin","full_name":"VIdeO-and-Language INference","num_papers_in_archive":18},{"url":"/dataset/fivr-200k","name":"FIVR-200K","full_name":"","num_papers_in_archive":16},{"url":"/dataset/tvc","name":"TVC","full_name":"TV show Captions","num_papers_in_archive":16},{"url":"/dataset/condensed-movies","name":"Condensed Movies","full_name":"","num_papers_in_archive":15},{"url":"/dataset/queryd","name":"QuerYD","full_name":"","num_papers_in_archive":15},{"url":"/dataset/egoexolearn","name":"EgoExoLearn","full_name":"","num_papers_in_archive":12},{"url":"/dataset/how2r","name":"How2R","full_name":"How2R","num_papers_in_archive":9},{"url":"/dataset/marine-video-kit","name":"MVK","full_name":"Marine Video Kit","num_papers_in_archive":9},{"url":"/dataset/hirest","name":"HiREST","full_name":"HIerarchical REtrieval and STep-captioning","num_papers_in_archive":7},{"url":"/dataset/chronomagic","name":"ChronoMagic","full_name":"","num_papers_in_archive":5},{"url":"/dataset/shot2story20k","name":"Shot2Story20K","full_name":"","num_papers_in_archive":3},{"url":"/dataset/chronomagic-pro","name":"ChronoMagic-Pro","full_name":"","num_papers_in_archive":2},{"url":"/dataset/vtc","name":"VTC","full_name":"Videos, Titles and Comments","num_papers_in_archive":2},{"url":"/dataset/chronomagic-proh","name":"ChronoMagic-ProH","full_name":"","num_papers_in_archive":1},{"url":"/dataset/ikea-assembly-in-the-wild-dataset","name":"IAW Dataset","full_name":"Ikea Assembly In The Wild Dataset","num_papers_in_archive":1},{"url":"/dataset/kinetic-gebc","name":"Kinetics-GEB+","full_name":"","num_papers_in_archive":1},{"url":"/dataset/msvd-indonesian","name":"MSVD-Indonesian","full_name":"","num_papers_in_archive":1},{"url":"/dataset/stvd","name":"STVD-PVCD","full_name":"Partial Video Copy Detection Dataset","num_papers_in_archive":1},{"url":"/dataset/vilt","name":"VILT","full_name":"Video Instructions Linking for Complex Tasks","num_papers_in_archive":1},{"url":"/dataset/win-fail-action-understanding","name":"Win-Fail Action Understanding","full_name":"Win-Fail Action Understanding","num_papers_in_archive":1}],"subtasks":[{"url":"/task/composed-video-retrieval-covr","name":"Composed Video Retrieval (CoVR)"},{"url":"/task/replay-grounding","name":"Replay Grounding"},{"url":"/task/video-adverb-retrieval","name":"Video-Adverb Retrieval"},{"url":"/task/video-grounding","name":"Video Grounding"},{"url":"/task/video-text-retrieval","name":"Video-Text Retrieval"}],"parent_tasks":[{"url":"/task/video","name":"Video"}],"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":5,"rows_per_page":100,"shown":100,"of":486,"of_with_code":255,"tagged_in_all":486,"counts":{"archive_papers_tagged":486,"with_a_code_link":255,"where_syntology_ran_a_sample":95,"not_listed_spam_title":0,"listed":486,"listed_where_code_ran":95,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":74,"every_run_a_failure_of_syntologys_instrument":21,"listed_with_a_run_with_no_instrument_failure":74,"listed_every_run_a_failure_of_syntologys_instrument":21,"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/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","repositories_listed":6,"syntology":{"n":17,"n_ran":10,"n_constructed":5,"n_ran_checked":9,"n_instrument":1,"n_unverified":7,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"phrase":"10 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","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"}},"official":null}},{"url":"/paper/eco-efficient-convolutional-network-for","slug":"eco-efficient-convolutional-network-for","title":"ECO: Efficient Convolutional Network for Online Video Understanding","date":"2018-04-24","arxiv_id":"1804.09066","repositories_listed":6,"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":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/eco-efficient-convolutional-network-for#ran","syntology_url":"https://syntology.ai/paper/1804.09066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.09066"}},"official":{"repos":["mzolfaghari/ECO-efficient-video-understanding"],"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/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/learning-a-text-video-embedding-from","slug":"learning-a-text-video-embedding-from","title":"Learning a Text-Video Embedding from Incomplete and Heterogeneous Data","date":"2018-04-07","arxiv_id":"1804.02516","repositories_listed":5,"syntology":null},{"url":"/paper/text-video-retrieval-with-disentangled","slug":"text-video-retrieval-with-disentangled","title":"Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment","date":"2023-05-20","arxiv_id":"2305.12218","repositories_listed":4,"syntology":{"n":23,"n_ran":15,"n_constructed":0,"n_ran_checked":7,"n_instrument":8,"n_unverified":8,"n_honours":4,"n_violates":0,"n_no_contract":3,"n_pointer_only":7,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 8 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/text-video-retrieval-with-disentangled#ran","syntology_url":"https://syntology.ai/paper/2305.12218","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.12218"}},"official":{"repos":["jpthu17/dicosa"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/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","repositories_listed":4,"syntology":{"n":16,"n_ran":12,"n_constructed":7,"n_ran_checked":11,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"12 ran (of which 7 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":4,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 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) · 1 unverified","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"}},"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"]}}},{"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/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","repositories_listed":4,"syntology":{"n":25,"n_ran":20,"n_constructed":0,"n_ran_checked":9,"n_instrument":11,"n_unverified":5,"n_honours":5,"n_violates":1,"n_no_contract":3,"n_pointer_only":11,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 5 honoured, 1 violated, 3 with no contract checked; 11 where Syntology's instrument failed) · 5 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":4,"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/expectation-maximization-contrastive-learning#ran","syntology_url":"https://syntology.ai/paper/2211.11427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.11427"}},"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"]}}},{"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/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","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 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; 1 where Syntology's instrument failed) · 0 unverified","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"}},"official":null}},{"url":"/paper/dense-captioning-events-in-videos","slug":"dense-captioning-events-in-videos","title":"Dense-Captioning Events in Videos","date":"2017-05-02","arxiv_id":"1705.00754","repositories_listed":4,"syntology":null},{"url":"/paper/tvlt-textless-vision-language-transformer","slug":"tvlt-textless-vision-language-transformer","title":"TVLT: Textless Vision-Language Transformer","date":"2022-09-28","arxiv_id":"2209.14156","repositories_listed":3,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tvlt-textless-vision-language-transformer#ran","syntology_url":"https://syntology.ai/paper/2209.14156","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.14156"}},"official":{"repos":["zinengtang/tvlt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 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; 1 where Syntology's instrument failed) · 1 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":3,"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":5,"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/mdmmt-multidomain-multimodal-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2103.10699","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.10699"}},"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"]}}},{"url":"/paper/on-semantic-similarity-in-video-retrieval","slug":"on-semantic-similarity-in-video-retrieval","title":"On Semantic Similarity in Video Retrieval","date":"2021-03-18","arxiv_id":"2103.10095","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/on-semantic-similarity-in-video-retrieval#ran","syntology_url":"https://syntology.ai/paper/2103.10095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.10095"}},"official":{"repos":["mwray/Semantic-Video-Retrieval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hero-hierarchical-encoder-for-video-language","slug":"hero-hierarchical-encoder-for-video-language","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","date":"2020-05-01","arxiv_id":"2005.00200","repositories_listed":3,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hero-hierarchical-encoder-for-video-language#ran","syntology_url":"https://syntology.ai/paper/2005.00200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00200"}},"official":{"repos":["linjieli222/HERO"],"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":["listed","official"]}}},{"url":"/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","repositories_listed":3,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","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"}},"official":null}},{"url":"/paper/improving-mae-against-cce-under-label-noise","slug":"improving-mae-against-cce-under-label-noise","title":"IMAE for Noise-Robust Learning: Mean Absolute Error Does Not Treat Examples Equally and Gradient Magnitude's Variance Matters","date":"2019-03-28","arxiv_id":"1903.12141","repositories_listed":3,"syntology":null},{"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/contextiq-a-multimodal-expert-based-video","slug":"contextiq-a-multimodal-expert-based-video","title":"ContextIQ: A Multimodal Expert-Based Video Retrieval System for Contextual Advertising","date":"2024-10-29","arxiv_id":"2410.22233","repositories_listed":2,"syntology":null},{"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/dgl-dynamic-global-local-prompt-tuning-for","slug":"dgl-dynamic-global-local-prompt-tuning-for","title":"DGL: Dynamic Global-Local Prompt Tuning for Text-Video Retrieval","date":"2024-01-19","arxiv_id":"2401.10588","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":1,"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/dgl-dynamic-global-local-prompt-tuning-for#ran","syntology_url":"https://syntology.ai/paper/2401.10588","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10588"}},"official":{"repos":["knightyxp/dgl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/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","repositories_listed":2,"syntology":null},{"url":"/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","repositories_listed":2,"syntology":null},{"url":"/paper/learning-multi-modal-representations-by","slug":"learning-multi-modal-representations-by","title":"Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures","date":"2023-07-27","arxiv_id":"2307.15220","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/learning-multi-modal-representations-by#ran","syntology_url":"https://syntology.ai/paper/2307.15220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.15220"}},"official":{"repos":["camma-public/peskavlp","camma-public/surgvlp"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/icsvr-investigating-compositional-and","slug":"icsvr-investigating-compositional-and","title":"ICSVR: Investigating Compositional and Syntactic Understanding in Video Retrieval Models","date":"2023-06-28","arxiv_id":"2306.16533","repositories_listed":2,"syntology":null},{"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/transvcl-attention-enhanced-video-copy","slug":"transvcl-attention-enhanced-video-copy","title":"TransVCL: Attention-enhanced Video Copy Localization Network with Flexible Supervision","date":"2022-11-23","arxiv_id":"2211.13090","repositories_listed":2,"syntology":null},{"url":"/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","repositories_listed":2,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","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"}},"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"]}}},{"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/fitclip-refining-large-scale-pretrained-image","slug":"fitclip-refining-large-scale-pretrained-image","title":"FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks","date":"2022-03-24","arxiv_id":"2203.13371","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/fitclip-refining-large-scale-pretrained-image#ran","syntology_url":"https://syntology.ai/paper/2203.13371","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.13371"}},"official":{"repos":["bryant1410/fitclip","bryant1410/tclip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-video-retrieval-models-with","slug":"learning-video-retrieval-models-with","title":"Learning video retrieval models with relevance-aware online mining","date":"2022-03-16","arxiv_id":"2203.08688","repositories_listed":2,"syntology":null},{"url":"/paper/revitalize-region-feature-for-democratizing","slug":"revitalize-region-feature-for-democratizing","title":"Revitalize Region Feature for Democratizing Video-Language Pre-training of Retrieval","date":"2022-03-15","arxiv_id":"2203.07720","repositories_listed":2,"syntology":null},{"url":"/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","repositories_listed":2,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":2,"n_honours":4,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 4 honoured, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","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"}},"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"]}}},{"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/video-joint-modelling-based-on-hierarchical","slug":"video-joint-modelling-based-on-hierarchical","title":"Video Joint Modelling Based on Hierarchical Transformer for Co-summarization","date":"2021-12-27","arxiv_id":"2112.13478","repositories_listed":2,"syntology":null},{"url":"/paper/tcgl-temporal-contrastive-graph-for-self","slug":"tcgl-temporal-contrastive-graph-for-self","title":"TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learning","date":"2021-12-07","arxiv_id":"2112.03587","repositories_listed":2,"syntology":null},{"url":"/paper/assistsr-affordance-centric-question-driven","slug":"assistsr-affordance-centric-question-driven","title":"AssistSR: Task-oriented Video Segment Retrieval for Personal AI Assistant","date":"2021-11-30","arxiv_id":"2111.15050","repositories_listed":2,"syntology":null},{"url":"/paper/video-content-classification-using-deep","slug":"video-content-classification-using-deep","title":"Video Content Classification using Deep Learning","date":"2021-11-27","arxiv_id":"2111.13813","repositories_listed":2,"syntology":null},{"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/visual-spatio-temporal-relation-enhanced","slug":"visual-spatio-temporal-relation-enhanced","title":"BiC-Net: Learning Efficient Spatio-Temporal Relation for Text-Video Retrieval","date":"2021-10-29","arxiv_id":"2110.15609","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/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","repositories_listed":2,"syntology":null},{"url":"/paper/self-supervised-video-representation-learning-5","slug":"self-supervised-video-representation-learning-5","title":"Self-supervised Video Representation Learning by Uncovering Spatio-temporal Statistics","date":"2020-08-31","arxiv_id":"2008.13426","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/self-supervised-video-representation-learning-5#ran","syntology_url":"https://syntology.ai/paper/2008.13426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.13426"}},"official":{"repos":["laura-wang/video_repres_sts"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/self-supervised-video-representation-learning-3","slug":"self-supervised-video-representation-learning-3","title":"Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework","date":"2020-08-06","arxiv_id":"2008.02531","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"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) · 0 unverified","sample_list":"/paper/self-supervised-video-representation-learning-3#ran","syntology_url":"https://syntology.ai/paper/2008.02531","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.02531"}},"official":{"repos":["BestJuly/Inter-intra-video-contrastive-learning"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/hysia-serving-dnn-based-video-to-retail","slug":"hysia-serving-dnn-based-video-to-retail","title":"Hysia: Serving DNN-Based Video-to-Retail Applications in Cloud","date":"2020-06-09","arxiv_id":"2006.05117","repositories_listed":2,"syntology":null},{"url":"/paper/targeted-attack-for-deep-hashing-based","slug":"targeted-attack-for-deep-hashing-based","title":"Targeted Attack for Deep Hashing based Retrieval","date":"2020-04-15","arxiv_id":"2004.07955","repositories_listed":2,"syntology":null},{"url":"/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","repositories_listed":2,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 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; 1 where Syntology's instrument failed) · 3 unverified","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"}},"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"]}}},{"url":"/paper/tvr-a-large-scale-dataset-for-video-subtitle","slug":"tvr-a-large-scale-dataset-for-video-subtitle","title":"TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval","date":"2020-01-24","arxiv_id":"2001.09099","repositories_listed":2,"syntology":{"n":19,"n_ran":19,"n_constructed":0,"n_ran_checked":13,"n_instrument":6,"n_unverified":0,"n_honours":4,"n_violates":0,"n_no_contract":9,"n_pointer_only":3,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 4 honoured, 0 violated, 9 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tvr-a-large-scale-dataset-for-video-subtitle#ran","syntology_url":"https://syntology.ai/paper/2001.09099","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.09099"}},"official":{"repos":["jayleicn/TVCaption","jayleicn/TVRetrieval"],"state":"official (archive's flag): 19 ran","n_ran":19,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 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; 1 where Syntology's instrument failed) · 1 unverified","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"}},"official":null}},{"url":"/paper/person-search-in-videos-with-one-portrait","slug":"person-search-in-videos-with-one-portrait","title":"Person Search in Videos with One Portrait Through Visual and Temporal Links","date":"2018-07-27","arxiv_id":"1807.10510","repositories_listed":2,"syntology":null},{"url":"/paper/hashing-with-mutual-information","slug":"hashing-with-mutual-information","title":"Hashing with Mutual Information","date":"2018-03-02","arxiv_id":"1803.00974","repositories_listed":2,"syntology":null},{"url":"/paper/learning-from-video-and-text-via-large-scale","slug":"learning-from-video-and-text-via-large-scale","title":"Learning from Video and Text via Large-Scale Discriminative Clustering","date":"2017-07-27","arxiv_id":"1707.09074","repositories_listed":2,"syntology":null},{"url":"/paper/from-play-to-replay-composed-video-retrieval","slug":"from-play-to-replay-composed-video-retrieval","title":"From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained Videos","date":"2025-06-05","arxiv_id":"2506.05274","repositories_listed":1,"syntology":null},{"url":"/paper/a-challenge-to-build-neuro-symbolic-video","slug":"a-challenge-to-build-neuro-symbolic-video","title":"A Challenge to Build Neuro-Symbolic Video Agents","date":"2025-05-20","arxiv_id":"2505.13851","repositories_listed":1,"syntology":null},{"url":"/paper/lovr-a-benchmark-for-long-video-retrieval-in","slug":"lovr-a-benchmark-for-long-video-retrieval-in","title":"LoVR: A Benchmark for Long Video Retrieval in Multimodal Contexts","date":"2025-05-20","arxiv_id":"2505.13928","repositories_listed":1,"syntology":null},{"url":"/paper/rebalancing-contrastive-alignment-with","slug":"rebalancing-contrastive-alignment-with","title":"Contrastive Alignment with Semantic Gap-Aware Corrections in Text-Video Retrieval","date":"2025-05-18","arxiv_id":"2505.12499","repositories_listed":1,"syntology":null},{"url":"/paper/video-gpt-via-next-clip-diffusion","slug":"video-gpt-via-next-clip-diffusion","title":"Video-GPT via Next Clip Diffusion","date":"2025-05-18","arxiv_id":"2505.12489","repositories_listed":1,"syntology":null},{"url":"/paper/respec-relevance-and-specificity-grounded","slug":"respec-relevance-and-specificity-grounded","title":"ReSpec: Relevance and Specificity Grounded Online Filtering for Learning on Video-Text Data Streams","date":"2025-04-21","arxiv_id":"2504.14875","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/respec-relevance-and-specificity-grounded#ran","syntology_url":"https://syntology.ai/paper/2504.14875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.14875"}},"official":{"repos":["cdjkim/respec"],"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"]}}},{"url":"/paper/towards-efficient-partially-relevant-video","slug":"towards-efficient-partially-relevant-video","title":"Towards Efficient Partially Relevant Video Retrieval with Active Moment Discovering","date":"2025-04-15","arxiv_id":"2504.10920","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-efficient-partially-relevant-video#ran","syntology_url":"https://syntology.ai/paper/2504.10920","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.10920"}},"official":{"repos":["songpipi/amdnet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tc-mgc-text-conditioned-multi-grained","slug":"tc-mgc-text-conditioned-multi-grained","title":"TC-MGC: Text-Conditioned Multi-Grained Contrastive Learning for Text-Video Retrieval","date":"2025-04-07","arxiv_id":"2504.04707","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tc-mgc-text-conditioned-multi-grained#ran","syntology_url":"https://syntology.ai/paper/2504.04707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.04707"}},"official":{"repos":["jingxiaolun/tc-mgc"],"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/enhancing-subsequent-video-retrieval-via","slug":"enhancing-subsequent-video-retrieval-via","title":"Enhancing Subsequent Video Retrieval via Vision-Language Models (VLMs)","date":"2025-03-21","arxiv_id":"2503.17415","repositories_listed":1,"syntology":null},{"url":"/paper/stablefusion-continual-video-retrieval-via","slug":"stablefusion-continual-video-retrieval-via","title":"StableFusion: Continual Video Retrieval via Frame Adaptation","date":"2025-03-13","arxiv_id":"2503.10111","repositories_listed":1,"syntology":null},{"url":"/paper/composed-multi-modal-retrieval-a-survey-of","slug":"composed-multi-modal-retrieval-a-survey-of","title":"Composed Multi-modal Retrieval: A Survey of Approaches and Applications","date":"2025-03-03","arxiv_id":"2503.01334","repositories_listed":1,"syntology":null},{"url":"/paper/videorope-what-makes-for-good-video-rotary","slug":"videorope-what-makes-for-good-video-rotary","title":"VideoRoPE: What Makes for Good Video Rotary Position Embedding?","date":"2025-02-07","arxiv_id":"2502.05173","repositories_listed":1,"syntology":{"n":17,"n_ran":16,"n_constructed":0,"n_ran_checked":13,"n_instrument":3,"n_unverified":1,"n_honours":4,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 4 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/videorope-what-makes-for-good-video-rotary#ran","syntology_url":"https://syntology.ai/paper/2502.05173","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.05173"}},"official":{"repos":["wiselnn570/videorope"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-banzhaf-interaction-for-general","slug":"hierarchical-banzhaf-interaction-for-general","title":"Hierarchical Banzhaf Interaction for General Video-Language Representation Learning","date":"2024-12-30","arxiv_id":"2412.20964","repositories_listed":1,"syntology":null},{"url":"/paper/video-rag-visually-aligned-retrieval","slug":"video-rag-visually-aligned-retrieval","title":"Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension","date":"2024-11-20","arxiv_id":"2411.13093","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/video-rag-visually-aligned-retrieval#ran","syntology_url":"https://syntology.ai/paper/2411.13093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.13093"}},"official":{"repos":["leon1207/video-rag-master"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community"]}}},{"url":"/paper/decomposing-relationship-from-1-to-n-into-n-1","slug":"decomposing-relationship-from-1-to-n-into-n-1","title":"Text Proxy: Decomposing Retrieval from a 1-to-N Relationship into N 1-to-1 Relationships for Text-Video Retrieval","date":"2024-10-09","arxiv_id":"2410.06618","repositories_listed":1,"syntology":null},{"url":"/paper/tokenbinder-text-video-retrieval-with-one-to","slug":"tokenbinder-text-video-retrieval-with-one-to","title":"TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm","date":"2024-09-30","arxiv_id":"2409.19865","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":3,"n_instrument":8,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 8 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tokenbinder-text-video-retrieval-with-one-to#ran","syntology_url":"https://syntology.ai/paper/2409.19865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19865"}},"official":{"repos":["bingqingzhang/TokenBinder"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tempme-video-temporal-token-merging-for","slug":"tempme-video-temporal-token-merging-for","title":"TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval","date":"2024-09-02","arxiv_id":"2409.01156","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":3,"n_ran_checked":4,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tempme-video-temporal-token-merging-for#ran","syntology_url":"https://syntology.ai/paper/2409.01156","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.01156"}},"official":null}},{"url":"/paper/t2vindexer-a-generative-video-indexer-for","slug":"t2vindexer-a-generative-video-indexer-for","title":"T2VIndexer: A Generative Video Indexer for Efficient Text-Video Retrieval","date":"2024-08-21","arxiv_id":"2408.11432","repositories_listed":1,"syntology":null},{"url":"/paper/muse-mamba-is-efficient-multi-scale-learner","slug":"muse-mamba-is-efficient-multi-scale-learner","title":"MUSE: Mamba is Efficient Multi-scale Learner for Text-video Retrieval","date":"2024-08-20","arxiv_id":"2408.10575","repositories_listed":1,"syntology":null},{"url":"/paper/egocvr-an-egocentric-benchmark-for-fine","slug":"egocvr-an-egocentric-benchmark-for-fine","title":"EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval","date":"2024-07-23","arxiv_id":"2407.16658","repositories_listed":1,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":4,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/egocvr-an-egocentric-benchmark-for-fine#ran","syntology_url":"https://syntology.ai/paper/2407.16658","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.16658"}},"official":{"repos":["explainableml/egocvr"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/seds-semantically-enhanced-dual-stream","slug":"seds-semantically-enhanced-dual-stream","title":"SEDS: Semantically Enhanced Dual-Stream Encoder for Sign Language Retrieval","date":"2024-07-23","arxiv_id":"2407.16394","repositories_listed":1,"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":0,"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/seds-semantically-enhanced-dual-stream#ran","syntology_url":"https://syntology.ai/paper/2407.16394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.16394"}},"official":{"repos":["longtaojiang/seds"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/meta-optimized-angular-margin-contrastive","slug":"meta-optimized-angular-margin-contrastive","title":"MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning","date":"2024-07-04","arxiv_id":"2407.03788","repositories_listed":1,"syntology":null},{"url":"/paper/referring-atomic-video-action-recognition","slug":"referring-atomic-video-action-recognition","title":"Referring Atomic Video Action Recognition","date":"2024-07-02","arxiv_id":"2407.01872","repositories_listed":1,"syntology":null},{"url":"/paper/explore-the-limits-of-omni-modal-pretraining","slug":"explore-the-limits-of-omni-modal-pretraining","title":"Explore the Limits of Omni-modal Pretraining at Scale","date":"2024-06-13","arxiv_id":"2406.09412","repositories_listed":1,"syntology":null},{"url":"/paper/gmmformer-v2-an-uncertainty-aware-framework","slug":"gmmformer-v2-an-uncertainty-aware-framework","title":"GMMFormer v2: An Uncertainty-aware Framework for Partially Relevant Video Retrieval","date":"2024-05-22","arxiv_id":"2405.13824","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":3,"n_instrument":7,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":10,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gmmformer-v2-an-uncertainty-aware-framework#ran","syntology_url":"https://syntology.ai/paper/2405.13824","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.13824"}},"official":{"repos":["huangmozhi9527/gmmformer_v2"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/text-video-retrieval-with-global-local","slug":"text-video-retrieval-with-global-local","title":"Text-Video Retrieval with Global-Local Semantic Consistent Learning","date":"2024-05-21","arxiv_id":"2405.12710","repositories_listed":1,"syntology":null},{"url":"/paper/composed-video-retrieval-via-enriched-context","slug":"composed-video-retrieval-via-enriched-context","title":"Composed Video Retrieval via Enriched Context and Discriminative Embeddings","date":"2024-03-25","arxiv_id":"2403.16997","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/composed-video-retrieval-via-enriched-context#ran","syntology_url":"https://syntology.ai/paper/2403.16997","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16997"}},"official":{"repos":["omkarthawakar/composed-video-retrieval"],"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"]}}},{"url":"/paper/egoexolearn-a-dataset-for-bridging","slug":"egoexolearn-a-dataset-for-bridging","title":"EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World","date":"2024-03-24","arxiv_id":"2403.16182","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/egoexolearn-a-dataset-for-bridging#ran","syntology_url":"https://syntology.ai/paper/2403.16182","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16182"}},"official":{"repos":["opengvlab/egoexolearn"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"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/improving-video-corpus-moment-retrieval-with","slug":"improving-video-corpus-moment-retrieval-with","title":"Improving Video Corpus Moment Retrieval with Partial Relevance Enhancement","date":"2024-02-21","arxiv_id":"2402.13576","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"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) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","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"}},"official":null}},{"url":"/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,"repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/shot2story20k-a-new-benchmark-for","slug":"shot2story20k-a-new-benchmark-for","title":"Shot2Story20K: A New Benchmark for Comprehensive Understanding of Multi-shot Videos","date":"2023-12-16","arxiv_id":"2312.10300","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/shot2story20k-a-new-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2312.10300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10300"}},"official":{"repos":["bytedance/Shot2Story"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/let-all-be-whitened-multi-teacher","slug":"let-all-be-whitened-multi-teacher","title":"Let All be Whitened: Multi-teacher Distillation for Efficient Visual Retrieval","date":"2023-12-15","arxiv_id":"2312.09716","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/let-all-be-whitened-multi-teacher#ran","syntology_url":"https://syntology.ai/paper/2312.09716","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.09716"}},"official":{"repos":["maryeon/whiten_mtd"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/waver-writing-style-agnostic-video-retrieval","slug":"waver-writing-style-agnostic-video-retrieval","title":"WAVER: Writing-style Agnostic Text-Video Retrieval via Distilling Vision-Language Models Through Open-Vocabulary Knowledge","date":"2023-12-15","arxiv_id":"2312.09507","repositories_listed":1,"syntology":null},{"url":"/paper/videocon-robust-video-language-alignment-via","slug":"videocon-robust-video-language-alignment-via","title":"VideoCon: Robust Video-Language Alignment via Contrast Captions","date":"2023-11-15","arxiv_id":"2311.10111","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/videocon-robust-video-language-alignment-via#ran","syntology_url":"https://syntology.ai/paper/2311.10111","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.10111"}},"official":{"repos":["hritikbansal/videocon"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/testa-temporal-spatial-token-aggregation-for","slug":"testa-temporal-spatial-token-aggregation-for","title":"TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding","date":"2023-10-29","arxiv_id":"2310.19060","repositories_listed":1,"syntology":{"n":15,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":4,"n_honours":3,"n_violates":0,"n_no_contract":6,"n_pointer_only":5,"phrase":"11 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; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/testa-temporal-spatial-token-aggregation-for#ran","syntology_url":"https://syntology.ai/paper/2310.19060","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.19060"}},"official":{"repos":["renshuhuai-andy/testa"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/joint-searching-and-grounding-multi","slug":"joint-searching-and-grounding-multi","title":"Joint Searching and Grounding: Multi-Granularity Video Content Retrieval","date":"2023-10-23","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/building-an-open-vocabulary-video-clip-model","slug":"building-an-open-vocabulary-video-clip-model","title":"Building an Open-Vocabulary Video CLIP Model with Better Architectures, Optimization and Data","date":"2023-10-08","arxiv_id":"2310.05010","repositories_listed":1,"syntology":null},{"url":"/paper/gmmformer-gaussian-mixture-model-based","slug":"gmmformer-gaussian-mixture-model-based","title":"GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrieval","date":"2023-10-08","arxiv_id":"2310.05195","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gmmformer-gaussian-mixture-model-based#ran","syntology_url":"https://syntology.ai/paper/2310.05195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05195"}},"official":{"repos":["huangmozhi9527/GMMFormer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/analyzing-zero-shot-abilities-of-vision","slug":"analyzing-zero-shot-abilities-of-vision","title":"Analyzing Zero-Shot Abilities of Vision-Language Models on Video Understanding Tasks","date":"2023-10-07","arxiv_id":"2310.04914","repositories_listed":1,"syntology":null}],"syntology_records":53,"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":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/video-retrieval-on-didemo","since_archive":"/sota/video-retrieval-on-didemo#since-judged","papers_judged":3,"placed":0},{"leaderboard":"/sota/video-retrieval-on-lsmdc","since_archive":"/sota/video-retrieval-on-lsmdc#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/video-retrieval-on-activitynet","since_archive":"/sota/video-retrieval-on-activitynet#since-judged","papers_judged":3,"placed":0},{"leaderboard":"/sota/video-retrieval-on-msvd","since_archive":"/sota/video-retrieval-on-msvd#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/video-retrieval-on-vatex","since_archive":"/sota/video-retrieval-on-vatex#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":95,"papers_where_code_ran_first_page":"/task/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":"archive","page":2,"of":5,"url":"/task/video-retrieval/papers/2","json":"/task/video-retrieval/papers/2.json","rows":100},{"order":"archive","page":3,"of":5,"url":"/task/video-retrieval/papers/3","json":"/task/video-retrieval/papers/3.json","rows":100},{"order":"archive","page":4,"of":5,"url":"/task/video-retrieval/papers/4","json":"/task/video-retrieval/papers/4.json","rows":100},{"order":"archive","page":5,"of":5,"url":"/task/video-retrieval/papers/5","json":"/task/video-retrieval/papers/5.json","rows":86},{"order":"ran","page":1,"of":1,"url":"/task/video-retrieval/papers/ran/1","json":"/task/video-retrieval/papers/ran/1.json","rows":95}],"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":"cd7d9ef757e674a3cffbb90fa76b999ea668f876536a3ca817279ebe9e04f480","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}