{"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/text-to-video-retrieval","name":"Text to Video Retrieval","slug":"text-to-video-retrieval","description_markdown":"She's gone \r\nI can't find her anywhere \r\nI'm looking everywhere for her\r\nEverywhere is dark","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":75,"papers_with_code":51,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":7,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/text-to-video-retrieval-on-kinetic-geb","slug":"text-to-video-retrieval-on-kinetic-geb","dataset":"Kinetics-GEB+","dataset_url":"/dataset/kinetic-gebc","rows_in_archive":2,"metrics":["mAP","text-to-video R@1","text-to-video R@10","text-to-video R@5","text-to-video R@50"],"first_row_in_archive_order":{"model":"FROZEN-revised","paper_title":"GEB+: A Benchmark for Generic Event Boundary Captioning, Grounding and Retrieval","paper_url":"/paper/generic-event-boundary-captioning-a-benchmark","paper_date":"2022-04-01","arxiv_id":"2204.00486","code_links":[{"title":"yuxuan-w/geb-plus","url":"https://github.com/yuxuan-w/geb-plus"}],"syntology":null}},{"leaderboard":"/sota/text-to-video-retrieval-on-msr-vtt","slug":"text-to-video-retrieval-on-msr-vtt","dataset":"MSR-VTT","dataset_url":"/dataset/msr-vtt","rows_in_archive":1,"metrics":["text-to-video R@1"],"first_row_in_archive_order":{"model":"CLIP4Clip","paper_title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","paper_url":"/paper/clip4clip-an-empirical-study-of-clip-for-end","paper_date":"2021-04-18","arxiv_id":"2104.08860","code_links":[{"title":"towhee-io/towhee","url":"https://github.com/towhee-io/towhee"},{"title":"ArrowLuo/CLIP4Clip","url":"https://github.com/ArrowLuo/CLIP4Clip"},{"title":"roudimit/AVLnet","url":"https://github.com/roudimit/AVLnet"},{"title":"facebookresearch/EgoTV","url":"https://github.com/facebookresearch/EgoTV"},{"title":"willard-yuan/video-text-retrieval-papers","url":"https://github.com/willard-yuan/video-text-retrieval-papers"}],"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"]}}}},{"leaderboard":"/sota/text-to-video-retrieval-on-msvd-indonesian","slug":"text-to-video-retrieval-on-msvd-indonesian","dataset":"MSVD-Indonesian","dataset_url":"/dataset/msvd-indonesian","rows_in_archive":1,"metrics":["R@1","R@5","R@10","Median Rank","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}}],"datasets":[{"url":"/dataset/kinetics","name":"Kinetics","full_name":"Kinetics Human Action Video Dataset","num_papers_in_archive":1341},{"url":"/dataset/msr-vtt","name":"MSR-VTT","full_name":"","num_papers_in_archive":640},{"url":"/dataset/marine-video-kit","name":"MVK","full_name":"Marine Video Kit","num_papers_in_archive":9},{"url":"/dataset/sakuga-42m","name":"Sakuga-42M","full_name":"","num_papers_in_archive":2},{"url":"/dataset/chinaopen","name":"ChinaOpen-1k","full_name":"","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}],"subtasks":[{"url":"/task/partially-relevant-video-retrieval","name":"Partially Relevant Video Retrieval"}],"parent_tasks":[{"url":"/task/10-shot-image-generation","name":"10-shot image generation"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":75,"of":75,"of_with_code":51,"tagged_in_all":75,"counts":{"archive_papers_tagged":75,"with_a_code_link":51,"where_syntology_ran_a_sample":22,"not_listed_spam_title":0,"listed":75,"listed_where_code_ran":22,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":16,"every_run_a_failure_of_syntologys_instrument":6,"listed_with_a_run_with_no_instrument_failure":16,"listed_every_run_a_failure_of_syntologys_instrument":6,"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/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/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/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/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/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/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/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/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/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/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/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/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/msvd-indonesian-a-benchmark-for-multimodal","slug":"msvd-indonesian-a-benchmark-for-multimodal","title":"MSVD-Indonesian: A Benchmark for Multimodal Video-Text Tasks in Indonesian","date":"2023-06-20","arxiv_id":"2306.11341","repositories_listed":1,"syntology":null},{"url":"/paper/meltr-meta-loss-transformer-for-learning-to","slug":"meltr-meta-loss-transformer-for-learning-to","title":"MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models","date":"2023-03-23","arxiv_id":"2303.13009","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"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) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/meltr-meta-loss-transformer-for-learning-to#ran","syntology_url":"https://syntology.ai/paper/2303.13009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.13009"}},"official":{"repos":["mlvlab/MELTR"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-end-to-end-video-question-answering","slug":"efficient-end-to-end-video-question-answering","title":"Efficient End-to-End Video Question Answering with Pyramidal Multimodal Transformer","date":"2023-02-04","arxiv_id":"2302.02136","repositories_listed":1,"syntology":null},{"url":"/paper/dual-learning-with-dynamic-knowledge","slug":"dual-learning-with-dynamic-knowledge","title":"Dual Learning with Dynamic Knowledge Distillation for Partially Relevant Video Retrieval","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/vindlu-a-recipe-for-effective-video-and","slug":"vindlu-a-recipe-for-effective-video-and","title":"VindLU: A Recipe for Effective Video-and-Language Pretraining","date":"2022-12-09","arxiv_id":"2212.05051","repositories_listed":1,"syntology":null},{"url":"/paper/are-all-combinations-equal-combining-textual","slug":"are-all-combinations-equal-combining-textual","title":"Are All Combinations Equal? Combining Textual and Visual Features with Multiple Space Learning for Text-Based Video Retrieval","date":"2022-11-21","arxiv_id":"2211.11351","repositories_listed":1,"syntology":null},{"url":"/paper/an-empirical-study-of-end-to-end-video","slug":"an-empirical-study-of-end-to-end-video","title":"An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling","date":"2022-09-04","arxiv_id":"2209.01540","repositories_listed":1,"syntology":null},{"url":"/paper/partially-relevant-video-retrieval","slug":"partially-relevant-video-retrieval","title":"Partially Relevant Video Retrieval","date":"2022-08-26","arxiv_id":"2208.12510","repositories_listed":1,"syntology":null},{"url":"/paper/clover-towards-a-unified-video-language","slug":"clover-towards-a-unified-video-language","title":"Clover: Towards A Unified Video-Language Alignment and Fusion Model","date":"2022-07-16","arxiv_id":"2207.07885","repositories_listed":1,"syntology":null},{"url":"/paper/multi-modal-robustness-analysis-against","slug":"multi-modal-robustness-analysis-against","title":"Robustness Analysis of Video-Language Models Against Visual and Language Perturbations","date":"2022-07-05","arxiv_id":"2207.02159","repositories_listed":1,"syntology":null},{"url":"/paper/rome-role-aware-mixture-of-expert-transformer","slug":"rome-role-aware-mixture-of-expert-transformer","title":"RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval","date":"2022-06-26","arxiv_id":"2206.12845","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-role-aware-correlation-transformer","slug":"semantic-role-aware-correlation-transformer","title":"Semantic Role Aware Correlation Transformer for Text to Video Retrieval","date":"2022-06-26","arxiv_id":"2206.12849","repositories_listed":1,"syntology":null},{"url":"/paper/lavender-unifying-video-language","slug":"lavender-unifying-video-language","title":"LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling","date":"2022-06-14","arxiv_id":"2206.07160","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/lavender-unifying-video-language#ran","syntology_url":"https://syntology.ai/paper/2206.07160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.07160"}},"official":{"repos":["microsoft/lavender"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/revisiting-the-video-in-video-language","slug":"revisiting-the-video-in-video-language","title":"Revisiting the \"Video\" in Video-Language Understanding","date":"2022-06-03","arxiv_id":"2206.01720","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/revisiting-the-video-in-video-language#ran","syntology_url":"https://syntology.ai/paper/2206.01720","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.01720"}},"official":null}},{"url":"/paper/learning-to-retrieve-videos-by-asking","slug":"learning-to-retrieve-videos-by-asking","title":"Learning to Retrieve Videos by Asking Questions","date":"2022-05-11","arxiv_id":"2205.05739","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/eclipse-efficient-long-range-video-retrieval","slug":"eclipse-efficient-long-range-video-retrieval","title":"ECLIPSE: Efficient Long-range Video Retrieval using Sight and Sound","date":"2022-04-06","arxiv_id":"2204.02874","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":5,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/eclipse-efficient-long-range-video-retrieval#ran","syntology_url":"https://syntology.ai/paper/2204.02874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02874"}},"official":{"repos":["GenjiB/ECLIPSE"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/generic-event-boundary-captioning-a-benchmark","slug":"generic-event-boundary-captioning-a-benchmark","title":"GEB+: A Benchmark for Generic Event Boundary Captioning, Grounding and Retrieval","date":"2022-04-01","arxiv_id":"2204.00486","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/reading-strategy-inspired-visual","slug":"reading-strategy-inspired-visual","title":"Reading-strategy Inspired Visual Representation Learning for Text-to-Video Retrieval","date":"2022-01-23","arxiv_id":"2201.09168","repositories_listed":1,"syntology":null},{"url":"/paper/lightweight-attentional-feature-fusion-for","slug":"lightweight-attentional-feature-fusion-for","title":"Lightweight Attentional Feature Fusion: A New Baseline for Text-to-Video Retrieval","date":"2021-12-03","arxiv_id":"2112.01832","repositories_listed":1,"syntology":null},{"url":"/paper/violet-end-to-end-video-language-transformers","slug":"violet-end-to-end-video-language-transformers","title":"VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling","date":"2021-11-24","arxiv_id":"2111.12681","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/violet-end-to-end-video-language-transformers#ran","syntology_url":"https://syntology.ai/paper/2111.12681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.12681"}},"official":{"repos":["tsujuifu/pytorch_violet"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/advancing-high-resolution-video-language","slug":"advancing-high-resolution-video-language","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","date":"2021-11-19","arxiv_id":"2111.10337","repositories_listed":1,"syntology":null},{"url":"/paper/value-a-multi-task-benchmark-for-video-and","slug":"value-a-multi-task-benchmark-for-video-and","title":"VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation","date":"2021-06-08","arxiv_id":"2106.04632","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/value-a-multi-task-benchmark-for-video-and#ran","syntology_url":"https://syntology.ai/paper/2106.04632","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.04632"}},"official":{"repos":["VALUE-Leaderboard/StarterCode"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/decembert-learning-from-noisy-instructional","slug":"decembert-learning-from-noisy-instructional","title":"DeCEMBERT: Learning from Noisy Instructional Videos via Dense Captions and Entropy Minimization","date":"2021-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-clustering-networks-for-self","slug":"multimodal-clustering-networks-for-self","title":"Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos","date":"2021-04-26","arxiv_id":"2104.12671","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":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/multimodal-clustering-networks-for-self#ran","syntology_url":"https://syntology.ai/paper/2104.12671","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.12671"}},"official":{"repos":["brian7685/Multimodal-Clustering-Network"],"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/less-is-more-clipbert-for-video-and-language","slug":"less-is-more-clipbert-for-video-and-language","title":"Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling","date":"2021-02-11","arxiv_id":"2102.06183","repositories_listed":1,"syntology":null},{"url":"/paper/the-end-of-end-to-end-a-video-understanding","slug":"the-end-of-end-to-end-a-video-understanding","title":"The End-of-End-to-End: A Video Understanding Pentathlon Challenge (2020)","date":"2020-08-03","arxiv_id":"2008.00744","repositories_listed":1,"syntology":null},{"url":"/paper/condensed-movies-story-based-retrieval-with","slug":"condensed-movies-story-based-retrieval-with","title":"Condensed Movies: Story Based Retrieval with Contextual Embeddings","date":"2020-05-08","arxiv_id":"2005.04208","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":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/condensed-movies-story-based-retrieval-with#ran","syntology_url":"https://syntology.ai/paper/2005.04208","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.04208"}},"official":null}},{"url":"/paper/noise-estimation-using-density-estimation-for","slug":"noise-estimation-using-density-estimation-for","title":"Noise Estimation Using Density Estimation for Self-Supervised Multimodal Learning","date":"2020-03-06","arxiv_id":"2003.03186","repositories_listed":1,"syntology":null},{"url":null,"slug":"q2e-query-to-event-decomposition-for-zero","title":"Q2E: Query-to-Event Decomposition for Zero-Shot Multilingual Text-to-Video Retrieval","date":"2025-06-11","arxiv_id":"2506.10202","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-auxiliary-information-in-text-to","title":"Leveraging Auxiliary Information in Text-to-Video Retrieval: A Review","date":"2025-05-29","arxiv_id":"2505.23952","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-colbert-contextualized-late-interaction-1","title":"Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval","date":"2025-03-24","arxiv_id":"2503.19009","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":"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-granularity-and-multi-modal-feature","title":"Multi-Granularity and Multi-modal Feature Interaction Approach for Text Video Retrieval","date":"2024-06-21","arxiv_id":"2407.12798","repositories_listed":0,"syntology":null},{"url":"/paper/sakuga-42m-dataset-scaling-up-cartoon","slug":"sakuga-42m-dataset-scaling-up-cartoon","title":"Sakuga-42M Dataset: Scaling Up Cartoon Research","date":"2024-05-13","arxiv_id":"2405.07425","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-text-to-video-retrieval-from-image","title":"Learning text-to-video retrieval from image captioning","date":"2024-04-26","arxiv_id":"2404.17498","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-vision-language-models-on-millions","title":"Distilling Vision-Language Models on Millions of Videos","date":"2024-01-11","arxiv_id":"2401.06129","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":null,"slug":"e-vilm-efficient-video-language-model-via","title":"E-ViLM: Efficient Video-Language Model via Masked Video Modeling with Semantic Vector-Quantized Tokenizer","date":"2023-11-28","arxiv_id":"2311.17267","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-empirical-study-of-frame-selection-for","title":"An Empirical Study of Frame Selection for Text-to-Video Retrieval","date":"2023-11-01","arxiv_id":"2311.00298","repositories_listed":0,"syntology":null},{"url":null,"slug":"teachclip-multi-grained-teaching-for","title":"TeachCLIP: Multi-Grained Teaching for Efficient Text-to-Video Retrieval","date":"2023-08-02","arxiv_id":"2308.01217","repositories_listed":0,"syntology":null},{"url":"/paper/audio-enhanced-text-to-video-retrieval-using","slug":"audio-enhanced-text-to-video-retrieval-using","title":"Audio-Enhanced Text-to-Video Retrieval using Text-Conditioned Feature Alignment","date":"2023-07-24","arxiv_id":"2307.12964","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-perceiving-video-language-pre","title":"Temporal Perceiving Video-Language Pre-training","date":"2023-01-18","arxiv_id":"2301.07463","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-trajectory-word-alignments-for-video","title":"Learning Trajectory-Word Alignments for Video-Language Tasks","date":"2023-01-05","arxiv_id":"2301.01953","repositories_listed":0,"syntology":null},{"url":"/paper/video-text-modeling-with-zero-shot-transfer","slug":"video-text-modeling-with-zero-shot-transfer","title":"VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners","date":"2022-12-09","arxiv_id":"2212.04979","repositories_listed":0,"syntology":null},{"url":null,"slug":"smaug-sparse-masked-autoencoder-for-efficient","title":"SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-training","date":"2022-11-21","arxiv_id":"2211.11446","repositories_listed":0,"syntology":null},{"url":null,"slug":"fighting-fire-with-fire-assessing-the","title":"Fighting FIRe with FIRE: Assessing the Validity of Text-to-Video Retrieval Benchmarks","date":"2022-10-10","arxiv_id":"2210.05038","repositories_listed":0,"syntology":null},{"url":"/paper/cots-collaborative-two-stream-vision-language","slug":"cots-collaborative-two-stream-vision-language","title":"COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval","date":"2022-04-15","arxiv_id":"2204.07441","repositories_listed":0,"syntology":null},{"url":"/paper/mdmmt-2-multidomain-multimodal-transformer","slug":"mdmmt-2-multidomain-multimodal-transformer","title":"MDMMT-2: Multidomain Multimodal Transformer for Video Retrieval, One More Step Towards Generalization","date":"2022-03-14","arxiv_id":"2203.07086","repositories_listed":0,"syntology":null},{"url":null,"slug":"cupid-adaptive-curation-of-pre-training-data","title":"CUPID: Adaptive Curation of Pre-training Data for Video-and-Language Representation Learning","date":"2021-04-01","arxiv_id":"2104.00285","repositories_listed":0,"syntology":null},{"url":null,"slug":"support-set-bottlenecks-for-video-text-1","title":"Support-set bottlenecks for video-text representation learning","date":"2020-10-06","arxiv_id":"2010.02824","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieving-and-highlighting-action-with","title":"Retrieving and Highlighting Action with Spatiotemporal Reference","date":"2020-05-19","arxiv_id":"2005.09183","repositories_listed":0,"syntology":null}],"syntology_records":24,"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":22,"papers_where_code_ran_first_page":"/task/text-to-video-retrieval/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/text-to-video-retrieval/papers/ran/1","json":"/task/text-to-video-retrieval/papers/ran/1.json","rows":22}],"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":"a7b7270a6c4200fba0f0b69f97723a675ab24c0a03954650de4b41674f25676d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}