{"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-text-retrieval","name":"Video-Text Retrieval","slug":"video-text-retrieval","description_markdown":"Video-Text retrieval requires understanding of both video and language together. Therefore it's different to video retrieval task.","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":111,"papers_with_code":59,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":6,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/video-text-retrieval-on-test-of-time","slug":"video-text-retrieval-on-test-of-time","dataset":"Test-of-Time","dataset_url":"/dataset/test-of-time","rows_in_archive":4,"metrics":["2-Class Accuracy"],"first_row_in_archive_order":{"model":"Video-LLAMA","paper_title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","paper_url":"/paper/video-llama-an-instruction-tuned-audio-visual","paper_date":"2023-06-05","arxiv_id":"2306.02858","code_links":[{"title":"damo-nlp-sg/video-llama","url":"https://github.com/damo-nlp-sg/video-llama"},{"title":"damo-nlp-sg/videollama2","url":"https://github.com/damo-nlp-sg/videollama2"},{"title":"damo-nlp-sg/videollama3","url":"https://github.com/damo-nlp-sg/videollama3"},{"title":"xinding-sys/StreamMind","url":"https://github.com/xinding-sys/StreamMind"}],"syntology":{"n":25,"n_ran":18,"n_constructed":7,"n_ran_checked":8,"n_instrument":10,"n_unverified":7,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":9,"phrase":"18 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/video-llama-an-instruction-tuned-audio-visual#ran","syntology_url":"https://syntology.ai/paper/2306.02858","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02858"}},"official":{"repos":["damo-nlp-sg/video-llama"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}}}],"datasets":[{"url":"/dataset/webvid","name":"WebVid","full_name":"","num_papers_in_archive":257},{"url":"/dataset/test-of-time","name":"Test-of-Time","full_name":"Test of Time Synthetic Video Dataset","num_papers_in_archive":5},{"url":"/dataset/symon","name":"SYMON","full_name":"Synopses of Movie Narratives","num_papers_in_archive":4},{"url":"/dataset/youku-mplug","name":"Youku-mPLUG","full_name":"","num_papers_in_archive":4},{"url":"/dataset/vtc","name":"VTC","full_name":"Videos, Titles and Comments","num_papers_in_archive":2},{"url":"/dataset/wonderbread","name":"wonderbread","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/video-retrieval","name":"Video Retrieval"}],"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":2,"rows_per_page":100,"shown":100,"of":111,"of_with_code":59,"tagged_in_all":111,"counts":{"archive_papers_tagged":111,"with_a_code_link":59,"where_syntology_ran_a_sample":25,"not_listed_spam_title":0,"listed":111,"listed_where_code_ran":25,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":22,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":22,"listed_every_run_a_failure_of_syntologys_instrument":3,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/languagebind-extending-video-language","slug":"languagebind-extending-video-language","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","date":"2023-10-03","arxiv_id":"2310.01852","repositories_listed":6,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":4,"n_honours":3,"n_violates":0,"n_no_contract":6,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/languagebind-extending-video-language#ran","syntology_url":"https://syntology.ai/paper/2310.01852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01852"}},"official":{"repos":["pku-yuangroup/languagebind"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/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/video-llama-an-instruction-tuned-audio-visual","slug":"video-llama-an-instruction-tuned-audio-visual","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","date":"2023-06-05","arxiv_id":"2306.02858","repositories_listed":4,"syntology":{"n":25,"n_ran":18,"n_constructed":7,"n_ran_checked":8,"n_instrument":10,"n_unverified":7,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":9,"phrase":"18 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/video-llama-an-instruction-tuned-audio-visual#ran","syntology_url":"https://syntology.ai/paper/2306.02858","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02858"}},"official":{"repos":["damo-nlp-sg/video-llama"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/fine-grained-video-text-retrieval-with","slug":"fine-grained-video-text-retrieval-with","title":"Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning","date":"2020-03-01","arxiv_id":"2003.00392","repositories_listed":4,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fine-grained-video-text-retrieval-with#ran","syntology_url":"https://syntology.ai/paper/2003.00392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.00392"}},"official":null}},{"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/mplug-effective-and-efficient-vision-language","slug":"mplug-effective-and-efficient-vision-language","title":"mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections","date":"2022-05-24","arxiv_id":"2205.12005","repositories_listed":3,"syntology":null},{"url":"/paper/internvl-scaling-up-vision-foundation-models","slug":"internvl-scaling-up-vision-foundation-models","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","date":"2023-12-21","arxiv_id":"2312.14238","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/internvl-scaling-up-vision-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2312.14238","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14238"}},"official":{"repos":["opengvlab/internvl"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/rgnet-a-unified-retrieval-and-grounding","slug":"rgnet-a-unified-retrieval-and-grounding","title":"RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos","date":"2023-12-11","arxiv_id":"2312.06729","repositories_listed":2,"syntology":null},{"url":"/paper/timechat-a-time-sensitive-multimodal-large","slug":"timechat-a-time-sensitive-multimodal-large","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","date":"2023-12-04","arxiv_id":"2312.02051","repositories_listed":2,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/timechat-a-time-sensitive-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2312.02051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02051"}},"official":{"repos":["renshuhuai-andy/timechat"],"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/uniadapter-unified-parameter-efficient","slug":"uniadapter-unified-parameter-efficient","title":"UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling","date":"2023-02-13","arxiv_id":"2302.06605","repositories_listed":2,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":1,"n_instrument":7,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":10,"phrase":"8 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; 7 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/uniadapter-unified-parameter-efficient#ran","syntology_url":"https://syntology.ai/paper/2302.06605","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.06605"}},"official":{"repos":["rerv/uniadapter","uniadapter/uniadapter"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/egocentric-video-language-pretraining","slug":"egocentric-video-language-pretraining","title":"Egocentric Video-Language Pretraining","date":"2022-06-03","arxiv_id":"2206.01670","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/egocentric-video-language-pretraining#ran","syntology_url":"https://syntology.ai/paper/2206.01670","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.01670"}},"official":{"repos":["showlab/egovlp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","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/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/discovla-discrepancy-reduction-in-vision-1","slug":"discovla-discrepancy-reduction-in-vision-1","title":"DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval","date":"2025-06-10","arxiv_id":"2506.08887","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 1 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","sample_list":"/paper/discovla-discrepancy-reduction-in-vision-1#ran","syntology_url":"https://syntology.ai/paper/2506.08887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.08887"}},"official":{"repos":["lunarshen/dsicovla"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/one-trajectory-one-token-grounded-video","slug":"one-trajectory-one-token-grounded-video","title":"One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory","date":"2025-05-29","arxiv_id":"2505.23617","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/temporal-working-memory-query-guided-segment","slug":"temporal-working-memory-query-guided-segment","title":"Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding","date":"2025-02-09","arxiv_id":"2502.06020","repositories_listed":1,"syntology":null},{"url":"/paper/expertized-caption-auto-enhancement-for-video","slug":"expertized-caption-auto-enhancement-for-video","title":"Expertized Caption Auto-Enhancement for Video-Text Retrieval","date":"2025-02-05","arxiv_id":"2502.02885","repositories_listed":1,"syntology":null},{"url":"/paper/reversed-in-time-a-novel-temporal-emphasized","slug":"reversed-in-time-a-novel-temporal-emphasized","title":"Reversed in Time: A Novel Temporal-Emphasized Benchmark for Cross-Modal Video-Text Retrieval","date":"2024-12-26","arxiv_id":"2412.19178","repositories_listed":1,"syntology":null},{"url":"/paper/carel-instruction-guided-reinforcement","slug":"carel-instruction-guided-reinforcement","title":"CAREL: Instruction-guided reinforcement learning with cross-modal auxiliary objectives","date":"2024-11-29","arxiv_id":"2411.19787","repositories_listed":1,"syntology":null},{"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/2407-21757","slug":"2407-21757","title":"Learning Video Context as Interleaved Multimodal Sequences","date":"2024-07-31","arxiv_id":"2407.21757","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"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, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2407-21757#ran","syntology_url":"https://syntology.ai/paper/2407.21757","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.21757"}},"official":{"repos":["showlab/movieseq"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/video-language-alignment-pre-training-via","slug":"video-language-alignment-pre-training-via","title":"Video-Language Alignment via Spatio-Temporal Graph Transformer","date":"2024-07-16","arxiv_id":"2407.11677","repositories_listed":1,"syntology":null},{"url":"/paper/diving-deep-into-the-motion-representation-of","slug":"diving-deep-into-the-motion-representation-of","title":"Diving Deep into the Motion Representation of Video-Text Models","date":"2024-06-07","arxiv_id":"2406.05075","repositories_listed":1,"syntology":null},{"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/m2-raap-a-multi-modal-recipe-for-advancing","slug":"m2-raap-a-multi-modal-recipe-for-advancing","title":"M2-RAAP: A Multi-Modal Recipe for Advancing Adaptation-based Pre-training towards Effective and Efficient Zero-shot Video-text Retrieval","date":"2024-01-31","arxiv_id":"2401.17797","repositories_listed":1,"syntology":null},{"url":"/paper/pros-prompting-to-simulate-generalized","slug":"pros-prompting-to-simulate-generalized","title":"ProS: Prompting-to-simulate Generalized knowledge for Universal Cross-Domain Retrieval","date":"2023-12-19","arxiv_id":"2312.12478","repositories_listed":1,"syntology":null},{"url":"/paper/harvest-video-foundation-models-via-efficient","slug":"harvest-video-foundation-models-via-efficient","title":"Harvest Video Foundation Models via Efficient Post-Pretraining","date":"2023-10-30","arxiv_id":"2310.19554","repositories_listed":1,"syntology":null},{"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/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/prototype-based-aleatoric-uncertainty-1","slug":"prototype-based-aleatoric-uncertainty-1","title":"Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval","date":"2023-09-29","arxiv_id":"2309.17093","repositories_listed":1,"syntology":{"n":19,"n_ran":17,"n_constructed":0,"n_ran_checked":9,"n_instrument":8,"n_unverified":2,"n_honours":5,"n_violates":1,"n_no_contract":3,"n_pointer_only":8,"phrase":"17 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; 8 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/prototype-based-aleatoric-uncertainty-1#ran","syntology_url":"https://syntology.ai/paper/2309.17093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17093"}},"official":{"repos":["leolee99/pau"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/unified-coarse-to-fine-alignment-for-video","slug":"unified-coarse-to-fine-alignment-for-video","title":"Unified Coarse-to-Fine Alignment for Video-Text Retrieval","date":"2023-09-18","arxiv_id":"2309.10091","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":5,"n_pointer_only":4,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unified-coarse-to-fine-alignment-for-video#ran","syntology_url":"https://syntology.ai/paper/2309.10091","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.10091"}},"official":{"repos":["ziyang412/ucofia"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/unipt-universal-parallel-tuning-for-transfer","slug":"unipt-universal-parallel-tuning-for-transfer","title":"UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory","date":"2023-08-28","arxiv_id":"2308.14316","repositories_listed":1,"syntology":null},{"url":"/paper/multi-event-video-text-retrieval","slug":"multi-event-video-text-retrieval","title":"Multi-event Video-Text Retrieval","date":"2023-08-22","arxiv_id":"2308.11551","repositories_listed":1,"syntology":{"n":18,"n_ran":15,"n_constructed":0,"n_ran_checked":8,"n_instrument":7,"n_unverified":3,"n_honours":4,"n_violates":1,"n_no_contract":3,"n_pointer_only":18,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 1 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multi-event-video-text-retrieval#ran","syntology_url":"https://syntology.ai/paper/2308.11551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11551"}},"official":{"repos":["gengyuanmax/mevtr"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/helping-hands-an-object-aware-ego-centric","slug":"helping-hands-an-object-aware-ego-centric","title":"Helping Hands: An Object-Aware Ego-Centric Video Recognition Model","date":"2023-08-15","arxiv_id":"2308.07918","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/helping-hands-an-object-aware-ego-centric#ran","syntology_url":"https://syntology.ai/paper/2308.07918","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.07918"}},"official":{"repos":["chuhanxx/helping_hand_for_egocentric_videos"],"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/global-and-local-semantic-completion-learning","slug":"global-and-local-semantic-completion-learning","title":"Global and Local Semantic Completion Learning for Vision-Language Pre-training","date":"2023-06-12","arxiv_id":"2306.07096","repositories_listed":1,"syntology":null},{"url":"/paper/svitt-temporal-learning-of-sparse-video-text","slug":"svitt-temporal-learning-of-sparse-video-text","title":"SViTT: Temporal Learning of Sparse Video-Text Transformers","date":"2023-04-18","arxiv_id":"2304.08809","repositories_listed":1,"syntology":null},{"url":"/paper/cico-domain-aware-sign-language-retrieval-via","slug":"cico-domain-aware-sign-language-retrieval-via","title":"CiCo: Domain-Aware Sign Language Retrieval via Cross-Lingual Contrastive Learning","date":"2023-03-22","arxiv_id":"2303.12793","repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-retrieval-with-partially","slug":"cross-modal-retrieval-with-partially","title":"Cross-Modal Retrieval with Partially Mismatched Pairs","date":"2023-02-22","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/video-text-retrieval-by-supervised-multi","slug":"video-text-retrieval-by-supervised-multi","title":"Video-Text Retrieval by Supervised Sparse Multi-Grained Learning","date":"2023-02-19","arxiv_id":"2302.09473","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-temporal-modeling-for-clip-based","slug":"revisiting-temporal-modeling-for-clip-based","title":"Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring","date":"2023-01-26","arxiv_id":"2301.11116","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-video-adapter-for-parameter","slug":"multimodal-video-adapter-for-parameter","title":"MV-Adapter: Multimodal Video Transfer Learning for Video Text Retrieval","date":"2023-01-19","arxiv_id":"2301.07868","repositories_listed":1,"syntology":null},{"url":"/paper/test-of-time-instilling-video-language-models","slug":"test-of-time-instilling-video-language-models","title":"Test of Time: Instilling Video-Language Models with a Sense of Time","date":"2023-01-05","arxiv_id":"2301.02074","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/test-of-time-instilling-video-language-models#ran","syntology_url":"https://syntology.ai/paper/2301.02074","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.02074"}},"official":{"repos":["bpiyush/TestOfTime"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/seeing-what-you-miss-vision-language-pre","slug":"seeing-what-you-miss-vision-language-pre","title":"Seeing What You Miss: Vision-Language Pre-training with Semantic Completion Learning","date":"2022-11-24","arxiv_id":"2211.13437","repositories_listed":1,"syntology":null},{"url":"/paper/vtc-improving-video-text-retrieval-with-user","slug":"vtc-improving-video-text-retrieval-with-user","title":"VTC: Improving Video-Text Retrieval with User Comments","date":"2022-10-19","arxiv_id":"2210.10820","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vtc-improving-video-text-retrieval-with-user#ran","syntology_url":"https://syntology.ai/paper/2210.10820","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.10820"}},"official":null}},{"url":"/paper/vision-language-pre-training-basics-recent","slug":"vision-language-pre-training-basics-recent","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","date":"2022-10-17","arxiv_id":"2210.09263","repositories_listed":1,"syntology":null},{"url":"/paper/clip-vip-adapting-pre-trained-image-text","slug":"clip-vip-adapting-pre-trained-image-text","title":"CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment","date":"2022-09-14","arxiv_id":"2209.06430","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":1,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/clip-vip-adapting-pre-trained-image-text#ran","syntology_url":"https://syntology.ai/paper/2209.06430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.06430"}},"official":{"repos":["microsoft/xpretrain"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/uni-perceiver-moe-learning-sparse-generalist","slug":"uni-perceiver-moe-learning-sparse-generalist","title":"Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs","date":"2022-06-09","arxiv_id":"2206.04674","repositories_listed":1,"syntology":null},{"url":"/paper/miles-visual-bert-pre-training-with-injected","slug":"miles-visual-bert-pre-training-with-injected","title":"MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval","date":"2022-04-26","arxiv_id":"2204.12408","repositories_listed":1,"syntology":null},{"url":"/paper/x-pool-cross-modal-language-video-attention","slug":"x-pool-cross-modal-language-video-attention","title":"X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval","date":"2022-03-28","arxiv_id":"2203.15086","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/x-pool-cross-modal-language-video-attention#ran","syntology_url":"https://syntology.ai/paper/2203.15086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15086"}},"official":{"repos":["layer6ai-labs/xpool"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/video-text-pre-training-with-learned-regions","slug":"video-text-pre-training-with-learned-regions","title":"Video-Text Pre-training with Learned Regions","date":"2021-12-02","arxiv_id":"2112.01194","repositories_listed":1,"syntology":null},{"url":"/paper/hanet-hierarchical-alignment-networks-for","slug":"hanet-hierarchical-alignment-networks-for","title":"HANet: Hierarchical Alignment Networks for Video-Text Retrieval","date":"2021-07-26","arxiv_id":"2107.12059","repositories_listed":1,"syntology":null},{"url":"/paper/clip2video-mastering-video-text-retrieval-via","slug":"clip2video-mastering-video-text-retrieval-via","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","date":"2021-06-21","arxiv_id":"2106.11097","repositories_listed":1,"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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/clip2video-mastering-video-text-retrieval-via#ran","syntology_url":"https://syntology.ai/paper/2106.11097","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11097"}},"official":{"repos":["CryhanFang/CLIP2Video"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/rudder-a-cross-lingual-video-and-text","slug":"rudder-a-cross-lingual-video-and-text","title":"Rudder: A Cross Lingual Video and Text Retrieval Dataset","date":"2021-03-09","arxiv_id":"2103.05457","repositories_listed":1,"syntology":null},{"url":"/paper/learning-the-best-pooling-strategy-for-visual","slug":"learning-the-best-pooling-strategy-for-visual","title":"Learning the Best Pooling Strategy for Visual Semantic Embedding","date":"2020-11-09","arxiv_id":"2011.04305","repositories_listed":1,"syntology":null},{"url":"/paper/coot-cooperative-hierarchical-transformer-for","slug":"coot-cooperative-hierarchical-transformer-for","title":"COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning","date":"2020-11-01","arxiv_id":"2011.00597","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/coot-cooperative-hierarchical-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2011.00597","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.00597"}},"official":{"repos":["gingsi/coot-videotext"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/polysemous-visual-semantic-embedding-for-1","slug":"polysemous-visual-semantic-embedding-for-1","title":"Polysemous Visual-Semantic Embedding for Cross-Modal Retrieval","date":"2019-06-11","arxiv_id":"1906.04402","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/polysemous-visual-semantic-embedding-for-1#ran","syntology_url":"https://syntology.ai/paper/1906.04402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.04402"}},"official":null}},{"url":"/paper/learning-joint-embedding-with-multimodal-cues","slug":"learning-joint-embedding-with-multimodal-cues","title":"Learning Joint Embedding with Multimodal Cues for Cross-Modal Video-Text Retrieval","date":"2018-06-11","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"towards-understanding-camera-motions-in-any","title":"Towards Understanding Camera Motions in Any Video","date":"2025-04-21","arxiv_id":"2504.15376","repositories_listed":0,"syntology":null},{"url":null,"slug":"lv-mae-learning-long-video-representations","title":"LV-MAE: Learning Long Video Representations through Masked-Embedding Autoencoders","date":"2025-04-04","arxiv_id":"2504.03501","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-audio-guided-video-representation","title":"Learning Audio-guided Video Representation with Gated Attention for Video-Text Retrieval","date":"2025-04-03","arxiv_id":"2504.02397","repositories_listed":0,"syntology":null},{"url":null,"slug":"v-2-dial-unification-of-video-and-visual","title":"V$^2$Dial: Unification of Video and Visual Dialog via Multimodal Experts","date":"2025-03-03","arxiv_id":"2503.02063","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-noisy-video-text-retrieval-via","title":"Rethinking Noisy Video-Text Retrieval via Relation-aware Alignment","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"v-2dial-unification-of-video-and-visual","title":"V^2Dial: Unification of Video and Visual Dialog via Multimodal Experts","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-video-text-retrieval-a-new","title":"CaReBench: A Fine-Grained Benchmark for Video Captioning and Retrieval","date":"2024-12-31","arxiv_id":"2501.00513","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-coarse-grained-matching-in-video-text","title":"Beyond Coarse-Grained Matching in Video-Text Retrieval","date":"2024-10-16","arxiv_id":"2410.12407","repositories_listed":0,"syntology":null},{"url":null,"slug":"navero-unlocking-fine-grained-semantics-for","title":"NAVERO: Unlocking Fine-Grained Semantics for Video-Language Compositionality","date":"2024-08-18","arxiv_id":"2408.09511","repositories_listed":0,"syntology":null},{"url":null,"slug":"ea-vtr-event-aware-video-text-retrieval","title":"EA-VTR: Event-Aware Video-Text Retrieval","date":"2024-07-10","arxiv_id":"2407.07478","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-scale-temporal-difference-transformer","title":"Multi-Scale Temporal Difference Transformer for Video-Text Retrieval","date":"2024-06-23","arxiv_id":"2406.16111","repositories_listed":0,"syntology":null},{"url":null,"slug":"henasy-learning-to-assemble-scene-entities","title":"HENASY: Learning to Assemble Scene-Entities for Egocentric Video-Language Model","date":"2024-06-01","arxiv_id":"2406.00307","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-aware-sign-language-video","title":"Uncertainty-aware sign language video retrieval with probability distribution modeling","date":"2024-05-30","arxiv_id":"2405.19689","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-empirical-study-of-excitation-and","title":"An Empirical Study of Excitation and Aggregation Design Adaptions in CLIP4Clip for Video-Text Retrieval","date":"2024-05-25","arxiv_id":"2406.01604","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-enhanced-zero-shot-video-captioning","title":"RETTA: Retrieval-Enhanced Test-Time Adaptation for Zero-Shot Video Captioning","date":"2024-05-11","arxiv_id":"2405.07046","repositories_listed":0,"syntology":null},{"url":"/paper/learning-with-noisy-correspondence","slug":"learning-with-noisy-correspondence","title":"Learning with Noisy Correspondence","date":"2024-04-13","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"havtr-improving-video-text-retrieval-through","title":"HaVTR: Improving Video-Text Retrieval Through Augmentation Using Large Foundation Models","date":"2024-04-07","arxiv_id":"2404.05083","repositories_listed":0,"syntology":null},{"url":null,"slug":"unifying-latent-and-lexicon-representations","title":"Unifying Latent and Lexicon Representations for Effective Video-Text Retrieval","date":"2024-02-26","arxiv_id":"2402.16769","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-editing-for-video-retrieval","title":"Video Editing for Video Retrieval","date":"2024-02-04","arxiv_id":"2402.02335","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-generative-language-models-for","title":"Leveraging Generative Language Models for Weakly Supervised Sentence Component Analysis in Video-Language Joint Learning","date":"2023-12-10","arxiv_id":"2312.06699","repositories_listed":0,"syntology":null},{"url":"/paper/videoprompter-an-ensemble-of-foundational","slug":"videoprompter-an-ensemble-of-foundational","title":"Videoprompter: an ensemble of foundational models for zero-shot video understanding","date":"2023-10-23","arxiv_id":"2310.15324","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-aware-alignment-network-for-cross","title":"Uncertainty-Aware Alignment Network for Cross-Domain Video-Text Retrieval","date":"2023-09-21","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-aware-alignment-network-for-cross-1","title":"Uncertainty-Aware Alignment Network for Cross-Domain Video-Text Retrieval","date":"2023-09-21","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"taca-upgrading-your-visual-foundation-model","title":"TaCA: Upgrading Your Visual Foundation Model with Task-agnostic Compatible Adapter","date":"2023-06-22","arxiv_id":"2306.12642","repositories_listed":0,"syntology":null},{"url":"/paper/vlab-enhancing-video-language-pre-training-by","slug":"vlab-enhancing-video-language-pre-training-by","title":"VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending","date":"2023-05-22","arxiv_id":"2305.13167","repositories_listed":0,"syntology":null},{"url":null,"slug":"mask-to-reconstruct-cooperative-semantics","title":"Mask to reconstruct: Cooperative Semantics Completion for Video-text Retrieval","date":"2023-05-13","arxiv_id":"2305.07910","repositories_listed":0,"syntology":null},{"url":"/paper/alternating-gradient-descent-and-mixture-of","slug":"alternating-gradient-descent-and-mixture-of","title":"Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception","date":"2023-05-10","arxiv_id":"2305.06324","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-for-video-text-retrieval-a","title":"Deep Learning for Video-Text Retrieval: a Review","date":"2023-02-24","arxiv_id":"2302.12552","repositories_listed":0,"syntology":null},{"url":null,"slug":"tagging-before-alignment-integrating-multi","title":"Tagging before Alignment: Integrating Multi-Modal Tags for Video-Text Retrieval","date":"2023-01-30","arxiv_id":"2301.12644","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-alignment-unsupervised-domain-adaptation","title":"Dual Alignment Unsupervised Domain Adaptation for Video-Text Retrieval","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hivlp-hierarchical-interactive-video-language","title":"HiVLP: Hierarchical Interactive Video-Language Pre-Training","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/vilem-visual-language-error-modeling-for","slug":"vilem-visual-language-error-modeling-for","title":"ViLEM: Visual-Language Error Modeling for Image-Text Retrieval","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/masked-contrastive-pre-training-for-efficient","slug":"masked-contrastive-pre-training-for-efficient","title":"Masked Contrastive Pre-Training for Efficient Video-Text Retrieval","date":"2022-12-02","arxiv_id":"2212.00986","repositories_listed":0,"syntology":null},{"url":null,"slug":"tokenflow-rethinking-fine-grained-cross-modal","title":"TokenFlow: Rethinking Fine-grained Cross-modal Alignment in Vision-Language Retrieval","date":"2022-09-28","arxiv_id":"2209.13822","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-loss-of-pair-similarity-optimization","title":"Unified Loss of Pair Similarity Optimization for Vision-Language Retrieval","date":"2022-09-28","arxiv_id":"2209.13869","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-adaptive-multiple-visual-prototype","title":"Text-Adaptive Multiple Visual Prototype Matching for Video-Text Retrieval","date":"2022-09-27","arxiv_id":"2209.13307","repositories_listed":0,"syntology":null},{"url":"/paper/omnivl-one-foundation-model-for-image","slug":"omnivl-one-foundation-model-for-image","title":"OmniVL:One Foundation Model for Image-Language and Video-Language Tasks","date":"2022-09-15","arxiv_id":"2209.07526","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-video-text-retrieval-with-explicit","title":"Boosting Video-Text Retrieval with Explicit High-Level Semantics","date":"2022-08-08","arxiv_id":"2208.04215","repositories_listed":0,"syntology":null},{"url":"/paper/lat-latent-translation-with-cycle-consistency","slug":"lat-latent-translation-with-cycle-consistency","title":"LaT: Latent Translation with Cycle-Consistency for Video-Text Retrieval","date":"2022-07-11","arxiv_id":"2207.04858","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalizing-multimodal-pre-training-into","title":"Generalizing Multimodal Pre-training into Multilingual via Language Acquisition","date":"2022-05-29","arxiv_id":"2206.11091","repositories_listed":0,"syntology":null},{"url":"/paper/synopses-of-movie-narratives-a-video-language-1","slug":"synopses-of-movie-narratives-a-video-language-1","title":"Synopses of Movie Narratives: a Video-Language Dataset for Story Understanding","date":"2022-03-11","arxiv_id":"2203.05711","repositories_listed":0,"syntology":null}],"syntology_records":26,"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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_where_code_ran":25,"papers_where_code_ran_first_page":"/task/video-text-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":2,"url":"/task/video-text-retrieval/papers/2","json":"/task/video-text-retrieval/papers/2.json","rows":11},{"order":"ran","page":1,"of":1,"url":"/task/video-text-retrieval/papers/ran/1","json":"/task/video-text-retrieval/papers/ran/1.json","rows":25}],"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":"0bebc06c214b05ae618a15913cd08804573420376dd918008583e1666b59bf4f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}