{"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/moment-retrieval","name":"Moment Retrieval","slug":"moment-retrieval","description_markdown":"Moment retrieval can de defined as the task of \"localizing moments in a video given a user query\".\r\n\r\nDescription from: [QVHIGHLIGHTS: Detecting Moments and Highlights in Videos via Natural Language Queries](https://arxiv.org/pdf/2107.09609v1.pdf)\r\n\r\nImage credit: [QVHIGHLIGHTS: Detecting Moments and Highlights in Videos via Natural Language Queries](https://arxiv.org/pdf/2107.09609v1.pdf)","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":132,"papers_with_code":76,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"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":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/moment-retrieval-on-qvhighlights","slug":"moment-retrieval-on-qvhighlights","dataset":"QVHighlights","dataset_url":"/dataset/qvhighlights","rows_in_archive":32,"metrics":["mAP","R@1 IoU=0.5","R@1 IoU=0.7","mAP@0.5","mAP@0.75"],"first_row_in_archive_order":{"model":"SG-DETR (w/ PT)","paper_title":"Saliency-Guided DETR for Moment Retrieval and Highlight Detection","paper_url":"/paper/saliency-guided-detr-for-moment-retrieval-and","paper_date":"2024-10-02","arxiv_id":"2410.01615","code_links":[{"title":"ai-forever/sg-detr","url":"https://github.com/ai-forever/sg-detr"}],"syntology":null}},{"leaderboard":"/sota/moment-retrieval-on-charades-sta","slug":"moment-retrieval-on-charades-sta","dataset":"Charades-STA","dataset_url":"/dataset/charades-sta","rows_in_archive":25,"metrics":["R@1 IoU=0.5","R@1 IoU=0.7","R@5 IoU=0.5","R@5 IoU=0.7","R@1 IoU=0.3","mIoU"],"first_row_in_archive_order":{"model":"SG-DETR (w/ PT)","paper_title":"Saliency-Guided DETR for Moment Retrieval and Highlight Detection","paper_url":"/paper/saliency-guided-detr-for-moment-retrieval-and","paper_date":"2024-10-02","arxiv_id":"2410.01615","code_links":[{"title":"ai-forever/sg-detr","url":"https://github.com/ai-forever/sg-detr"}],"syntology":null}}],"datasets":[{"url":"/dataset/charades-sta","name":"Charades-STA","full_name":"","num_papers_in_archive":236},{"url":"/dataset/qvhighlights","name":"QVHighlights","full_name":"Query-based Video Highlights","num_papers_in_archive":41},{"url":"/dataset/mad","name":"MAD","full_name":"","num_papers_in_archive":36},{"url":"/dataset/hirest","name":"HiREST","full_name":"HIerarchical REtrieval and STep-captioning","num_papers_in_archive":7},{"url":"/dataset/goal","name":"Goal","full_name":"","num_papers_in_archive":4},{"url":"/dataset/longvale","name":"LongVALE","full_name":"","num_papers_in_archive":2}],"subtasks":[{"url":"/task/zero-shot-moment-retrieval","name":"Zero-shot Moment Retrieval"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":132,"of_with_code":76,"tagged_in_all":132,"counts":{"archive_papers_tagged":132,"with_a_code_link":76,"where_syntology_ran_a_sample":33,"not_listed_spam_title":0,"listed":132,"listed_where_code_ran":33,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":29,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":29,"listed_every_run_a_failure_of_syntologys_instrument":4,"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/qvhighlights-detecting-moments-and-highlights","slug":"qvhighlights-detecting-moments-and-highlights","title":"QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries","date":"2021-07-20","arxiv_id":"2107.09609","repositories_listed":4,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/qvhighlights-detecting-moments-and-highlights#ran","syntology_url":"https://syntology.ai/paper/2107.09609","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.09609"}},"official":{"repos":["jayleicn/moment_detr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/umt-unified-multi-modal-transformers-for","slug":"umt-unified-multi-modal-transformers-for","title":"UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection","date":"2022-03-23","arxiv_id":"2203.12745","repositories_listed":3,"syntology":null},{"url":"/paper/hero-hierarchical-encoder-for-video-language","slug":"hero-hierarchical-encoder-for-video-language","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","date":"2020-05-01","arxiv_id":"2005.00200","repositories_listed":3,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hero-hierarchical-encoder-for-video-language#ran","syntology_url":"https://syntology.ai/paper/2005.00200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00200"}},"official":{"repos":["linjieli222/HERO"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/internvideo2-scaling-video-foundation-models","slug":"internvideo2-scaling-video-foundation-models","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","date":"2024-03-22","arxiv_id":"2403.15377","repositories_listed":2,"syntology":null},{"url":"/paper/correlation-guided-query-dependency","slug":"correlation-guided-query-dependency","title":"Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding","date":"2023-11-15","arxiv_id":"2311.08835","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":2,"n_no_contract":1,"n_pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/correlation-guided-query-dependency#ran","syntology_url":"https://syntology.ai/paper/2311.08835","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.08835"}},"official":{"repos":["wjun0830/cgdetr"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/tvr-a-large-scale-dataset-for-video-subtitle","slug":"tvr-a-large-scale-dataset-for-video-subtitle","title":"TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval","date":"2020-01-24","arxiv_id":"2001.09099","repositories_listed":2,"syntology":{"n":19,"n_ran":19,"n_constructed":0,"n_ran_checked":13,"n_instrument":6,"n_unverified":0,"n_honours":4,"n_violates":0,"n_no_contract":9,"n_pointer_only":3,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 4 honoured, 0 violated, 9 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tvr-a-large-scale-dataset-for-video-subtitle#ran","syntology_url":"https://syntology.ai/paper/2001.09099","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.09099"}},"official":{"repos":["jayleicn/TVCaption","jayleicn/TVRetrieval"],"state":"official (archive's flag): 19 ran","n_ran":19,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/temporal-localization-of-moments-in-video","slug":"temporal-localization-of-moments-in-video","title":"Finding Moments in Video Collections Using Natural Language","date":"2019-07-30","arxiv_id":"1907.12763","repositories_listed":2,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/temporal-localization-of-moments-in-video#ran","syntology_url":"https://syntology.ai/paper/1907.12763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.12763"}},"official":null}},{"url":"/paper/timeloc-a-unified-end-to-end-framework-for","slug":"timeloc-a-unified-end-to-end-framework-for","title":"TimeLoc: A Unified End-to-End Framework for Precise Timestamp Localization in Long Videos","date":"2025-03-09","arxiv_id":"2503.06526","repositories_listed":1,"syntology":null},{"url":"/paper/moment-of-untruth-dealing-with-negative","slug":"moment-of-untruth-dealing-with-negative","title":"Moment of Untruth: Dealing with Negative Queries in Video Moment Retrieval","date":"2025-02-12","arxiv_id":"2502.08544","repositories_listed":1,"syntology":null},{"url":"/paper/ld-detr-loop-decoder-detection-transformer","slug":"ld-detr-loop-decoder-detection-transformer","title":"LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detection","date":"2025-01-18","arxiv_id":"2501.10787","repositories_listed":1,"syntology":null},{"url":"/paper/a-flexible-and-scalable-framework-for-video","slug":"a-flexible-and-scalable-framework-for-video","title":"A Flexible and Scalable Framework for Video Moment Search","date":"2025-01-09","arxiv_id":"2501.05072","repositories_listed":1,"syntology":null},{"url":"/paper/watch-video-catch-keyword-context-aware","slug":"watch-video-catch-keyword-context-aware","title":"Watch Video, Catch Keyword: Context-aware Keyword Attention for Moment Retrieval and Highlight Detection","date":"2025-01-05","arxiv_id":"2501.02504","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":0,"n_instrument":8,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":10,"phrase":"8 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; 8 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/watch-video-catch-keyword-context-aware#ran","syntology_url":"https://syntology.ai/paper/2501.02504","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.02504"}},"official":{"repos":["visualaikhu/keyword-detr"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/anchor-aware-similarity-cohesion-in-target","slug":"anchor-aware-similarity-cohesion-in-target","title":"Anchor-Aware Similarity Cohesion in Target Frames Enables Predicting Temporal Moment Boundaries in 2D","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dtos-dynamic-time-object-sensing-with-large","slug":"dtos-dynamic-time-object-sensing-with-large","title":"DTOS: Dynamic Time Object Sensing with Large Multimodal Model","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/length-aware-detr-for-robust-moment-retrieval","slug":"length-aware-detr-for-robust-moment-retrieval","title":"Length-Aware DETR for Robust Moment Retrieval","date":"2024-12-30","arxiv_id":"2412.20816","repositories_listed":1,"syntology":null},{"url":"/paper/flashvtg-feature-layering-and-adaptive-score","slug":"flashvtg-feature-layering-and-adaptive-score","title":"FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding","date":"2024-12-18","arxiv_id":"2412.13441","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":2,"n_no_contract":2,"n_pointer_only":13,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 2 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/flashvtg-feature-layering-and-adaptive-score#ran","syntology_url":"https://syntology.ai/paper/2412.13441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.13441"}},"official":{"repos":["zhuo-cao/flashvtg"],"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/videolights-feature-refinement-and-cross-task","slug":"videolights-feature-refinement-and-cross-task","title":"VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrieval","date":"2024-12-02","arxiv_id":"2412.01558","repositories_listed":1,"syntology":null},{"url":"/paper/vid-morp-video-moment-retrieval-pretraining","slug":"vid-morp-video-moment-retrieval-pretraining","title":"Vid-Morp: Video Moment Retrieval Pretraining from Unlabeled Videos in the Wild","date":"2024-12-01","arxiv_id":"2412.00811","repositories_listed":1,"syntology":null},{"url":"/paper/llava-mr-large-language-and-vision-assistant","slug":"llava-mr-large-language-and-vision-assistant","title":"LLaVA-MR: Large Language-and-Vision Assistant for Video Moment Retrieval","date":"2024-11-21","arxiv_id":"2411.14505","repositories_listed":1,"syntology":null},{"url":"/paper/number-it-temporal-grounding-videos-like","slug":"number-it-temporal-grounding-videos-like","title":"Number it: Temporal Grounding Videos like Flipping Manga","date":"2024-11-15","arxiv_id":"2411.10332","repositories_listed":1,"syntology":{"n":11,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/number-it-temporal-grounding-videos-like#ran","syntology_url":"https://syntology.ai/paper/2411.10332","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10332"}},"official":{"repos":["yongliang-wu/numpro"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/timesuite-improving-mllms-for-long-video","slug":"timesuite-improving-mllms-for-long-video","title":"TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning","date":"2024-10-25","arxiv_id":"2410.19702","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/timesuite-improving-mllms-for-long-video#ran","syntology_url":"https://syntology.ai/paper/2410.19702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.19702"}},"official":null}},{"url":"/paper/verified-a-video-corpus-moment-retrieval","slug":"verified-a-video-corpus-moment-retrieval","title":"VERIFIED: A Video Corpus Moment Retrieval Benchmark for Fine-Grained Video Understanding","date":"2024-10-11","arxiv_id":"2410.08593","repositories_listed":1,"syntology":null},{"url":"/paper/saliency-guided-detr-for-moment-retrieval-and","slug":"saliency-guided-detr-for-moment-retrieval-and","title":"Saliency-Guided DETR for Moment Retrieval and Highlight Detection","date":"2024-10-02","arxiv_id":"2410.01615","repositories_listed":1,"syntology":null},{"url":"/paper/show-and-guide-instructional-plan-grounded","slug":"show-and-guide-instructional-plan-grounded","title":"Show and Guide: Instructional-Plan Grounded Vision and Language Model","date":"2024-09-27","arxiv_id":"2409.19074","repositories_listed":1,"syntology":null},{"url":"/paper/language-based-audio-moment-retrieval","slug":"language-based-audio-moment-retrieval","title":"Language-based Audio Moment Retrieval","date":"2024-09-24","arxiv_id":"2409.15672","repositories_listed":1,"syntology":null},{"url":"/paper/2408-02901","slug":"2408-02901","title":"Lighthouse: A User-Friendly Library for Reproducible Video Moment Retrieval and Highlight Detection","date":"2024-08-06","arxiv_id":"2408.02901","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":7,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/2408-02901#ran","syntology_url":"https://syntology.ai/paper/2408.02901","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.02901"}},"official":{"repos":["line/lighthouse"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/prior-knowledge-integration-via-llm-encoding","slug":"prior-knowledge-integration-via-llm-encoding","title":"Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval","date":"2024-07-21","arxiv_id":"2407.15051","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":2,"n_no_contract":1,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/prior-knowledge-integration-via-llm-encoding#ran","syntology_url":"https://syntology.ai/paper/2407.15051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.15051"}},"official":{"repos":["fletcherjiang/llmepet"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/tvr-ranking-a-dataset-for-ranked-video-moment","slug":"tvr-ranking-a-dataset-for-ranked-video-moment","title":"TVR-Ranking: A Dataset for Ranked Video Moment Retrieval with Imprecise Queries","date":"2024-07-09","arxiv_id":"2407.06597","repositories_listed":1,"syntology":null},{"url":"/paper/shine-saliency-aware-hierarchical-negative","slug":"shine-saliency-aware-hierarchical-negative","title":"SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding","date":"2024-07-06","arxiv_id":"2407.05118","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":5,"n_pointer_only":13,"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) · 2 unverified","sample_list":"/paper/shine-saliency-aware-hierarchical-negative#ran","syntology_url":"https://syntology.ai/paper/2407.05118","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.05118"}},"official":{"repos":["zxccade/shine"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/the-surprising-effectiveness-of-multimodal","slug":"the-surprising-effectiveness-of-multimodal","title":"The Surprising Effectiveness of Multimodal Large Language Models for Video Moment Retrieval","date":"2024-06-26","arxiv_id":"2406.18113","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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/the-surprising-effectiveness-of-multimodal#ran","syntology_url":"https://syntology.ai/paper/2406.18113","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18113"}},"official":{"repos":["sudo-Boris/mr-Blip"],"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/vtg-llm-integrating-timestamp-knowledge-into","slug":"vtg-llm-integrating-timestamp-knowledge-into","title":"VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal Grounding","date":"2024-05-22","arxiv_id":"2405.13382","repositories_listed":1,"syntology":{"n":17,"n_ran":15,"n_constructed":0,"n_ran_checked":5,"n_instrument":10,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 10 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/vtg-llm-integrating-timestamp-knowledge-into#ran","syntology_url":"https://syntology.ai/paper/2405.13382","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.13382"}},"official":{"repos":["gyxxyg/vtg-llm"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mlp-motion-label-prior-for-temporal-sentence","slug":"mlp-motion-label-prior-for-temporal-sentence","title":"MLP: Motion Label Prior for Temporal Sentence Localization in Untrimmed 3D Human Motions","date":"2024-04-21","arxiv_id":"2404.13657","repositories_listed":1,"syntology":null},{"url":"/paper/task-driven-exploration-decoupling-and-inter","slug":"task-driven-exploration-decoupling-and-inter","title":"Task-Driven Exploration: Decoupling and Inter-Task Feedback for Joint Moment Retrieval and Highlight Detection","date":"2024-04-14","arxiv_id":"2404.09263","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":10,"phrase":"8 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; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/task-driven-exploration-decoupling-and-inter#ran","syntology_url":"https://syntology.ai/paper/2404.09263","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09263"}},"official":{"repos":["edengabriel/taskweave"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/unimd-towards-unifying-moment-retrieval-and","slug":"unimd-towards-unifying-moment-retrieval-and","title":"UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection","date":"2024-04-07","arxiv_id":"2404.04933","repositories_listed":1,"syntology":null},{"url":"/paper/r-2-tuning-efficient-image-to-video-transfer","slug":"r-2-tuning-efficient-image-to-video-transfer","title":"R^2-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding","date":"2024-04-02","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/r-2-tuning-efficient-image-to-video-transfer-1","slug":"r-2-tuning-efficient-image-to-video-transfer-1","title":"$R^2$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding","date":"2024-03-31","arxiv_id":"2404.00801","repositories_listed":1,"syntology":null},{"url":"/paper/video-mamba-suite-state-space-model-as-a","slug":"video-mamba-suite-state-space-model-as-a","title":"Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding","date":"2024-03-14","arxiv_id":"2403.09626","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/video-mamba-suite-state-space-model-as-a#ran","syntology_url":"https://syntology.ai/paper/2403.09626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09626"}},"official":{"repos":["opengvlab/video-mamba-suite"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-video-corpus-moment-retrieval-with","slug":"improving-video-corpus-moment-retrieval-with","title":"Improving Video Corpus Moment Retrieval with Partial Relevance Enhancement","date":"2024-02-21","arxiv_id":"2402.13576","repositories_listed":1,"syntology":null},{"url":"/paper/tr-detr-task-reciprocal-transformer-for-joint","slug":"tr-detr-task-reciprocal-transformer-for-joint","title":"TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detection","date":"2024-01-04","arxiv_id":"2401.02309","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_constructed":5,"n_ran_checked":9,"n_instrument":4,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":7,"n_pointer_only":17,"phrase":"13 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/tr-detr-task-reciprocal-transformer-for-joint#ran","syntology_url":"https://syntology.ai/paper/2401.02309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.02309"}},"official":{"repos":["mingyao1120/tr-detr"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":5,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-balanced-alignment-modal-enhanced","slug":"towards-balanced-alignment-modal-enhanced","title":"Towards Balanced Alignment: Modal-Enhanced Semantic Modeling for Video Moment Retrieval","date":"2023-12-19","arxiv_id":"2312.12155","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-balanced-alignment-modal-enhanced#ran","syntology_url":"https://syntology.ai/paper/2312.12155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12155"}},"official":{"repos":["lntzm/mesm"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cross-modal-contrastive-learning-with","slug":"cross-modal-contrastive-learning-with","title":"Cross-modal Contrastive Learning with Asymmetric Co-attention Network for Video Moment Retrieval","date":"2023-12-12","arxiv_id":"2312.07435","repositories_listed":1,"syntology":null},{"url":"/paper/bam-detr-boundary-aligned-moment-detection","slug":"bam-detr-boundary-aligned-moment-detection","title":"BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos","date":"2023-11-30","arxiv_id":"2312.00083","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/bam-detr-boundary-aligned-moment-detection#ran","syntology_url":"https://syntology.ai/paper/2312.00083","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00083"}},"official":{"repos":["Pilhyeon/BAM-DETR"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/bridging-the-gap-a-unified-video","slug":"bridging-the-gap-a-unified-video","title":"Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection","date":"2023-11-28","arxiv_id":"2311.16464","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/bridging-the-gap-a-unified-video#ran","syntology_url":"https://syntology.ai/paper/2311.16464","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.16464"}},"official":{"repos":["easonxiao-888/uvcom"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/language-conditioned-change-point-detection","slug":"language-conditioned-change-point-detection","title":"Language-Conditioned Change-point Detection to Identify Sub-Tasks in Robotics Domains","date":"2023-09-01","arxiv_id":"2309.00743","repositories_listed":1,"syntology":null},{"url":"/paper/unloc-a-unified-framework-for-video","slug":"unloc-a-unified-framework-for-video","title":"UnLoc: A Unified Framework for Video Localization Tasks","date":"2023-08-21","arxiv_id":"2308.11062","repositories_listed":1,"syntology":null},{"url":"/paper/mvmr-evaluating-natural-language-video","slug":"mvmr-evaluating-natural-language-video","title":"MVMR: A New Framework for Evaluating Faithfulness of Video Moment Retrieval against Multiple Distractors","date":"2023-08-15","arxiv_id":"2309.16701","repositories_listed":1,"syntology":null},{"url":"/paper/univtg-towards-unified-video-language","slug":"univtg-towards-unified-video-language","title":"UniVTG: Towards Unified Video-Language Temporal Grounding","date":"2023-07-31","arxiv_id":"2307.16715","repositories_listed":1,"syntology":{"n":16,"n_ran":11,"n_constructed":2,"n_ran_checked":9,"n_instrument":2,"n_unverified":5,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":5,"phrase":"11 ran (of which 2 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/univtg-towards-unified-video-language#ran","syntology_url":"https://syntology.ai/paper/2307.16715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.16715"}},"official":{"repos":["showlab/univtg"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":2,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/momentdiff-generative-video-moment-retrieval","slug":"momentdiff-generative-video-moment-retrieval","title":"MomentDiff: Generative Video Moment Retrieval from Random to Real","date":"2023-07-06","arxiv_id":"2307.02869","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/momentdiff-generative-video-moment-retrieval#ran","syntology_url":"https://syntology.ai/paper/2307.02869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.02869"}},"official":{"repos":["imccretrieval/momentdiff"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/overcoming-weak-visual-textual-alignment-for","slug":"overcoming-weak-visual-textual-alignment-for","title":"Background-aware Moment Detection for Video Moment Retrieval","date":"2023-06-05","arxiv_id":"2306.02728","repositories_listed":1,"syntology":null},{"url":"/paper/joint-moment-retrieval-and-highlight","slug":"joint-moment-retrieval-and-highlight","title":"Joint Moment Retrieval and Highlight Detection Via Natural Language Queries","date":"2023-05-08","arxiv_id":"2305.04961","repositories_listed":1,"syntology":null},{"url":"/paper/tmr-text-to-motion-retrieval-using","slug":"tmr-text-to-motion-retrieval-using","title":"TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis","date":"2023-05-02","arxiv_id":"2305.00976","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":3,"n_instrument":6,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/tmr-text-to-motion-retrieval-using#ran","syntology_url":"https://syntology.ai/paper/2305.00976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.00976"}},"official":null}},{"url":"/paper/boundary-denoising-for-video-activity","slug":"boundary-denoising-for-video-activity","title":"Boundary-Denoising for Video Activity Localization","date":"2023-04-06","arxiv_id":"2304.02934","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-video-moment-retrieval-and-step","slug":"hierarchical-video-moment-retrieval-and-step","title":"Hierarchical Video-Moment Retrieval and Step-Captioning","date":"2023-03-29","arxiv_id":"2303.16406","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":2,"n_honours":1,"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; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/hierarchical-video-moment-retrieval-and-step#ran","syntology_url":"https://syntology.ai/paper/2303.16406","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16406"}},"official":{"repos":["j-min/HiREST"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/query-dependent-video-representation-for","slug":"query-dependent-video-representation-for","title":"Query-Dependent Video Representation for Moment Retrieval and Highlight Detection","date":"2023-03-24","arxiv_id":"2303.13874","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":1,"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/query-dependent-video-representation-for#ran","syntology_url":"https://syntology.ai/paper/2303.13874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.13874"}},"official":{"repos":["wjun0830/qd-detr"],"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/towards-diverse-temporal-grounding-under","slug":"towards-diverse-temporal-grounding-under","title":"Towards Diverse Temporal Grounding under Single Positive Labels","date":"2023-03-12","arxiv_id":"2303.06545","repositories_listed":1,"syntology":null},{"url":"/paper/are-binary-annotations-sufficient-video","slug":"are-binary-annotations-sufficient-video","title":"Are Binary Annotations Sufficient? Video Moment Retrieval via Hierarchical Uncertainty-Based Active Learning","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/exploring-temporal-concurrency-for-video","slug":"exploring-temporal-concurrency-for-video","title":"Exploring Temporal Concurrency for Video-Language Representation Learning","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/going-for-goal-a-resource-for-grounded","slug":"going-for-goal-a-resource-for-grounded","title":"Going for GOAL: A Resource for Grounded Football Commentaries","date":"2022-11-08","arxiv_id":"2211.04534","repositories_listed":1,"syntology":null},{"url":"/paper/modal-specific-pseudo-query-generation-for","slug":"modal-specific-pseudo-query-generation-for","title":"Modal-specific Pseudo Query Generation for Video Corpus Moment Retrieval","date":"2022-10-23","arxiv_id":"2210.12617","repositories_listed":1,"syntology":null},{"url":"/paper/selective-query-guided-debiasing-network-for","slug":"selective-query-guided-debiasing-network-for","title":"Selective Query-guided Debiasing for Video Corpus Moment Retrieval","date":"2022-10-17","arxiv_id":"2210.08714","repositories_listed":1,"syntology":{"n":24,"n_ran":6,"n_constructed":2,"n_ran_checked":5,"n_instrument":1,"n_unverified":18,"n_honours":3,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 18 unverified","sample_list":"/paper/selective-query-guided-debiasing-network-for#ran","syntology_url":"https://syntology.ai/paper/2210.08714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.08714"}},"official":{"repos":["dbstjswo505/SQuiDNet"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":2,"n_ran_no_instrument_failure":5,"n_unverified":18,"ran_from_kinds":["official"]}}},{"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/you-need-to-read-again-multi-granularity","slug":"you-need-to-read-again-multi-granularity","title":"You Need to Read Again: Multi-granularity Perception Network for Moment Retrieval in Videos","date":"2022-05-25","arxiv_id":"2205.12886","repositories_listed":1,"syntology":null},{"url":"/paper/video-moment-retrieval-from-text-queries-via","slug":"video-moment-retrieval-from-text-queries-via","title":"Video Moment Retrieval from Text Queries via Single Frame Annotation","date":"2022-04-20","arxiv_id":"2204.09409","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/video-moment-retrieval-from-text-queries-via#ran","syntology_url":"https://syntology.ai/paper/2204.09409","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.09409"}},"official":{"repos":["r-cui/ViGA"],"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":["official"]}}},{"url":"/paper/detecting-moments-and-highlights-in-videos","slug":"detecting-moments-and-highlights-in-videos","title":"Detecting Moments and Highlights in Videos via Natural Language Queries","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mad-a-scalable-dataset-for-language-grounding","slug":"mad-a-scalable-dataset-for-language-grounding","title":"MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions","date":"2021-12-01","arxiv_id":"2112.00431","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/mad-a-scalable-dataset-for-language-grounding#ran","syntology_url":"https://syntology.ai/paper/2112.00431","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.00431"}},"official":{"repos":["Soldelli/MAD"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/conquer-contextual-query-aware-ranking-for","slug":"conquer-contextual-query-aware-ranking-for","title":"CONQUER: Contextual Query-aware Ranking for Video Corpus Moment Retrieval","date":"2021-09-21","arxiv_id":"2109.10016","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/conquer-contextual-query-aware-ranking-for#ran","syntology_url":"https://syntology.ai/paper/2109.10016","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.10016"}},"official":{"repos":["houzhijian/conquer"],"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/mtvr-multilingual-moment-retrieval-in-videos","slug":"mtvr-multilingual-moment-retrieval-in-videos","title":"MTVR: Multilingual Moment Retrieval in Videos","date":"2021-07-30","arxiv_id":"2108.00061","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":4,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":10,"phrase":"7 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mtvr-multilingual-moment-retrieval-in-videos#ran","syntology_url":"https://syntology.ai/paper/2108.00061","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.00061"}},"official":{"repos":["jayleicn/mTVRetrieval"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":4,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/deconfounded-video-moment-retrieval-with","slug":"deconfounded-video-moment-retrieval-with","title":"Deconfounded Video Moment Retrieval with Causal Intervention","date":"2021-06-03","arxiv_id":"2106.01534","repositories_listed":1,"syntology":null},{"url":"/paper/video-corpus-moment-retrieval-with","slug":"video-corpus-moment-retrieval-with","title":"Video Corpus Moment Retrieval with Contrastive Learning","date":"2021-05-13","arxiv_id":"2105.06247","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":5,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/video-corpus-moment-retrieval-with#ran","syntology_url":"https://syntology.ai/paper/2105.06247","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.06247"}},"official":null}},{"url":"/paper/vlg-net-video-language-graph-matching-network","slug":"vlg-net-video-language-graph-matching-network","title":"VLG-Net: Video-Language Graph Matching Network for Video Grounding","date":"2020-11-19","arxiv_id":"2011.10132","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vlg-net-video-language-graph-matching-network#ran","syntology_url":"https://syntology.ai/paper/2011.10132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.10132"}},"official":null}},{"url":"/paper/frame-wise-cross-modal-match-for-video-moment","slug":"frame-wise-cross-modal-match-for-video-moment","title":"Frame-wise Cross-modal Matching for Video Moment Retrieval","date":"2020-09-22","arxiv_id":"2009.10434","repositories_listed":1,"syntology":null},{"url":"/paper/uncovering-hidden-challenges-in-query-based","slug":"uncovering-hidden-challenges-in-query-based","title":"Uncovering Hidden Challenges in Query-Based Video Moment Retrieval","date":"2020-09-01","arxiv_id":"2009.00325","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/uncovering-hidden-challenges-in-query-based#ran","syntology_url":"https://syntology.ai/paper/2009.00325","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.00325"}},"official":null}},{"url":"/paper/vlanet-video-language-alignment-network-for","slug":"vlanet-video-language-alignment-network-for","title":"VLANet: Video-Language Alignment Network for Weakly-Supervised Video Moment Retrieval","date":"2020-08-24","arxiv_id":"2008.10238","repositories_listed":1,"syntology":null},{"url":"/paper/regularized-two-branch-proposal-networks-for","slug":"regularized-two-branch-proposal-networks-for","title":"Regularized Two-Branch Proposal Networks for Weakly-Supervised Moment Retrieval in Videos","date":"2020-08-19","arxiv_id":"2008.08257","repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-interaction-networks-for-query","slug":"cross-modal-interaction-networks-for-query","title":"Cross-Modal Interaction Networks for Query-Based Moment Retrieval in Videos","date":"2019-06-06","arxiv_id":"1906.02497","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-video-moment-retrieval-from","slug":"weakly-supervised-video-moment-retrieval-from","title":"Weakly Supervised Video Moment Retrieval From Text Queries","date":"2019-04-05","arxiv_id":"1904.03282","repositories_listed":1,"syntology":null},{"url":"/paper/despite-exploring-contrastive-deep-skeleton","slug":"despite-exploring-contrastive-deep-skeleton","title":"DeSPITE: Exploring Contrastive Deep Skeleton-Pointcloud-IMU-Text Embeddings for Advanced Point Cloud Human Activity Understanding","date":"2025-06-16","arxiv_id":"2506.13897","repositories_listed":0,"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/despite-exploring-contrastive-deep-skeleton#ran","syntology_url":"https://syntology.ai/paper/2506.13897","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.13897"}},"official":null}},{"url":null,"slug":"retrieval-augmented-generation-evaluation-for","title":"Retrieval Augmented Generation Evaluation for Health Documents","date":"2025-05-07","arxiv_id":"2505.04680","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounding-md-grounded-video-language-pre","title":"Grounding-MD: Grounded Video-language Pre-training for Open-World Moment Detection","date":"2025-04-20","arxiv_id":"2504.14553","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-efficient-and-robust-moment-retrieval","title":"Towards Efficient and Robust Moment Retrieval System: A Unified Framework for Multi-Granularity Models and Temporal Reranking","date":"2025-04-11","arxiv_id":"2504.08384","repositories_listed":0,"syntology":null},{"url":null,"slug":"momentseeker-a-comprehensive-benchmark-and-a","title":"MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval","date":"2025-02-18","arxiv_id":"2502.12558","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-fusion-and-query-refinement","title":"Multi-modal Fusion and Query Refinement Network for Video Moment Retrieval and Highlight Detection","date":"2025-01-18","arxiv_id":"2501.10692","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-video-moment-retrieval-via-off-the","title":"Zero-shot Video Moment Retrieval via Off-the-shelf Multimodal Large Language Models","date":"2025-01-14","arxiv_id":"2501.07972","repositories_listed":0,"syntology":null},{"url":"/paper/the-devil-is-in-the-spurious-correlation","slug":"the-devil-is-in-the-spurious-correlation","title":"The Devil is in the Spurious Correlation: Boosting Moment Retrieval via Temporal Dynamic Learning","date":"2025-01-13","arxiv_id":"2501.07305","repositories_listed":0,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":8,"phrase":"8 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; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/the-devil-is-in-the-spurious-correlation#ran","syntology_url":"https://syntology.ai/paper/2501.07305","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.07305"}},"official":null}},{"url":null,"slug":"dave-diverse-atomic-visual-elements-dataset","title":"DAVE: Diverse Atomic Visual Elements Dataset with High Representation of Vulnerable Road Users in Complex and Unpredictable Environments","date":"2024-12-28","arxiv_id":"2412.20042","repositories_listed":0,"syntology":null},{"url":null,"slug":"query-centric-audio-visual-cognition-network","title":"Query-centric Audio-Visual Cognition Network for Moment Retrieval, Segmentation and Step-Captioning","date":"2024-12-18","arxiv_id":"2412.13543","repositories_listed":0,"syntology":null},{"url":null,"slug":"agent-based-video-trimming","title":"Agent-based Video Trimming","date":"2024-12-12","arxiv_id":"2412.09513","repositories_listed":0,"syntology":null},{"url":null,"slug":"eagle-egocentric-aggregated-language-video","title":"EAGLE: Egocentric AGgregated Language-video Engine","date":"2024-09-26","arxiv_id":"2409.17523","repositories_listed":0,"syntology":null},{"url":null,"slug":"d-m-enriching-e-commerce-videos-with-sound","title":"D&M: Enriching E-commerce Videos with Sound Effects by Key Moment Detection and SFX Matching","date":"2024-08-23","arxiv_id":"2408.13226","repositories_listed":0,"syntology":null},{"url":null,"slug":"qd-vmr-query-debiasing-with-contextual","title":"QD-VMR: Query Debiasing with Contextual Understanding Enhancement for Video Moment Retrieval","date":"2024-08-23","arxiv_id":"2408.12981","repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangle-and-denoise-tackling-context","title":"Disentangle and denoise: Tackling context misalignment for video moment retrieval","date":"2024-08-14","arxiv_id":"2408.07600","repositories_listed":0,"syntology":null},{"url":null,"slug":"slvideo-a-sign-language-video-moment","title":"SLVideo: A Sign Language Video Moment Retrieval Framework","date":"2024-07-22","arxiv_id":"2407.15668","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-sentence-video-grounding-for-long-video","title":"Multi-sentence Video Grounding for Long Video Generation","date":"2024-07-18","arxiv_id":"2407.13219","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":"mllm-as-video-narrator-mitigating-modality","title":"MLLM as Video Narrator: Mitigating Modality Imbalance in Video Moment Retrieval","date":"2024-06-25","arxiv_id":"2406.17880","repositories_listed":0,"syntology":null},{"url":null,"slug":"2dp-2mrc-2-dimensional-pointer-based-machine","title":"2DP-2MRC: 2-Dimensional Pointer-based Machine Reading Comprehension Method for Multimodal Moment Retrieval","date":"2024-06-10","arxiv_id":"2406.06201","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-learning-video-moment-retrieval-across","title":"Hybrid-Learning Video Moment Retrieval across Multi-Domain Labels","date":"2024-06-03","arxiv_id":"2406.01791","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-enhanced-video-moment-retrieval-with","title":"Context-Enhanced Video Moment Retrieval with Large Language Models","date":"2024-05-21","arxiv_id":"2405.12540","repositories_listed":0,"syntology":null},{"url":null,"slug":"gptsee-enhancing-moment-retrieval-and","title":"GPTSee: Enhancing Moment Retrieval and Highlight Detection via Description-Based Similarity Features","date":"2024-03-03","arxiv_id":"2403.01437","repositories_listed":0,"syntology":null},{"url":null,"slug":"event-aware-video-corpus-moment-retrieval","title":"Event-aware Video Corpus Moment Retrieval","date":"2024-02-21","arxiv_id":"2402.13566","repositories_listed":0,"syntology":null}],"syntology_records":35,"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":5,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/moment-retrieval-on-qvhighlights","since_archive":"/sota/moment-retrieval-on-qvhighlights#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/moment-retrieval-on-charades-sta","since_archive":"/sota/moment-retrieval-on-charades-sta#since-judged","papers_judged":4,"placed":0}]},"papers_where_code_ran":33,"papers_where_code_ran_first_page":"/task/moment-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/moment-retrieval/papers/2","json":"/task/moment-retrieval/papers/2.json","rows":32},{"order":"ran","page":1,"of":1,"url":"/task/moment-retrieval/papers/ran/1","json":"/task/moment-retrieval/papers/ran/1.json","rows":33}],"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":"dcffacac114150486cd9150c1cbd81ff7f708ffecc9e6dd7e57b2d2b0c577299","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}