{"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/highlight-detection","name":"Highlight Detection","slug":"highlight-detection","description_markdown":"https://youtu.be/pJ0auP7dbcY?si=vSiZevfJ57YUKC2q","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":78,"papers_with_code":41,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"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":2,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/highlight-detection-on-qvhighlights","slug":"highlight-detection-on-qvhighlights","dataset":"QVHighlights","dataset_url":"/dataset/qvhighlights","rows_in_archive":21,"metrics":["mAP","Hit@1"],"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/highlight-detection-on-tvsum","slug":"highlight-detection-on-tvsum","dataset":"TvSum","dataset_url":"/dataset/tvsum","rows_in_archive":7,"metrics":["mAP"],"first_row_in_archive_order":{"model":"FlashVTG","paper_title":"FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding","paper_url":"/paper/flashvtg-feature-layering-and-adaptive-score","paper_date":"2024-12-18","arxiv_id":"2412.13441","code_links":[{"title":"zhuo-cao/flashvtg","url":"https://github.com/zhuo-cao/flashvtg"}],"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"]}}}},{"leaderboard":"/sota/highlight-detection-on-youtube-highlights","slug":"highlight-detection-on-youtube-highlights","dataset":"YouTube Highlights","dataset_url":null,"rows_in_archive":7,"metrics":["mAP"],"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/highlight-detection-on-arabiska","slug":"highlight-detection-on-arabiska","dataset":"arabiska","dataset_url":null,"rows_in_archive":1,"metrics":["0..5sec"],"first_row_in_archive_order":{"model":"Kenan Kanan","paper_title":"100,000 Podcasts: A Spoken English Document Corpus","paper_url":"/paper/100000-podcasts-a-spoken-english-document","paper_date":"2020-12-01","arxiv_id":null,"code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/qvhighlights","name":"QVHighlights","full_name":"Query-based Video Highlights","num_papers_in_archive":41},{"url":"/dataset/tvsum","name":"TvSum","full_name":"TVSum: Summarizing Web Videos Using Titles","num_papers_in_archive":28}],"subtasks":[],"parent_tasks":[{"url":"/task/16k","name":"16k"}],"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":78,"of":78,"of_with_code":41,"tagged_in_all":78,"counts":{"archive_papers_tagged":78,"with_a_code_link":41,"where_syntology_ran_a_sample":18,"not_listed_spam_title":0,"listed":78,"listed_where_code_ran":18,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":17,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":17,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/timechat-a-time-sensitive-multimodal-large","slug":"timechat-a-time-sensitive-multimodal-large","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","date":"2023-12-04","arxiv_id":"2312.02051","repositories_listed":2,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/timechat-a-time-sensitive-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2312.02051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02051"}},"official":{"repos":["renshuhuai-andy/timechat"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/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/rhapsody-a-dataset-for-highlight-detection-in","slug":"rhapsody-a-dataset-for-highlight-detection-in","title":"Rhapsody: A Dataset for Highlight Detection in Podcasts","date":"2025-05-26","arxiv_id":"2505.19429","repositories_listed":1,"syntology":null},{"url":"/paper/tempura-temporal-event-masked-prediction-and","slug":"tempura-temporal-event-masked-prediction-and","title":"TEMPURA: Temporal Event Masked Prediction and Understanding for Reasoning in Action","date":"2025-05-02","arxiv_id":"2505.01583","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/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/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/video-repurposing-from-user-generated-content","slug":"video-repurposing-from-user-generated-content","title":"Video Repurposing from User Generated Content: A Large-scale Dataset and Benchmark","date":"2024-12-12","arxiv_id":"2412.08879","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"10 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; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/video-repurposing-from-user-generated-content#ran","syntology_url":"https://syntology.ai/paper/2412.08879","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.08879"}},"official":{"repos":["yongliang-wu/repurpose"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"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/videollm-knows-when-to-speak-enhancing-time","slug":"videollm-knows-when-to-speak-enhancing-time","title":"VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format","date":"2024-11-27","arxiv_id":"2411.17991","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/videollm-knows-when-to-speak-enhancing-time#ran","syntology_url":"https://syntology.ai/paper/2411.17991","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17991"}},"official":{"repos":["yellow-binary-tree/mmduet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/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/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/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/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/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/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/unleash-the-potential-of-clip-for-video","slug":"unleash-the-potential-of-clip-for-video","title":"Unleash the Potential of CLIP for Video Highlight Detection","date":"2024-04-02","arxiv_id":"2404.01745","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unleash-the-potential-of-clip-for-video#ran","syntology_url":"https://syntology.ai/paper/2404.01745","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01745"}},"official":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/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/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/joint-network-for-specular-highlight","slug":"joint-network-for-specular-highlight","title":"Joint network for specular highlight detection and adversarial generation of specular-free images trained with polarimetric data","date":"2023-11-28","arxiv_id":null,"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/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/mh-detr-video-moment-and-highlight-detection","slug":"mh-detr-video-moment-and-highlight-detection","title":"MH-DETR: Video Moment and Highlight Detection with Cross-modal Transformer","date":"2023-04-29","arxiv_id":"2305.00355","repositories_listed":1,"syntology":null},{"url":"/paper/collaborative-noisy-label-cleaner-learning","slug":"collaborative-noisy-label-cleaner-learning","title":"Collaborative Noisy Label Cleaner: Learning Scene-aware Trailers for Multi-modal Highlight Detection in Movies","date":"2023-03-26","arxiv_id":"2303.14768","repositories_listed":1,"syntology":null},{"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/specseg-network-for-specular-highlight","slug":"specseg-network-for-specular-highlight","title":"SpecSeg Network for Specular Highlight Detection and Segmentation in Real-World Images","date":"2022-08-30","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/m2-net-multi-stages-specular-highlight","slug":"m2-net-multi-stages-specular-highlight","title":"M2-Net: Multi-stages Specular Highlight Detection and Removal in Multi-scenes","date":"2022-07-20","arxiv_id":"2207.09965","repositories_listed":1,"syntology":null},{"url":"/paper/single-image-specular-highlight-removal-via","slug":"single-image-specular-highlight-removal-via","title":"Single-Image Specular Highlight Removal via Real-World Dataset Construction","date":"2021-08-27","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cross-category-video-highlight-detection-via","slug":"cross-category-video-highlight-detection-via","title":"Cross-category Video Highlight Detection via Set-based Learning","date":"2021-08-26","arxiv_id":"2108.11770","repositories_listed":1,"syntology":null},{"url":"/paper/text-aware-single-image-specular-highlight","slug":"text-aware-single-image-specular-highlight","title":"Text-Aware Single Image Specular Highlight Removal","date":"2021-08-16","arxiv_id":"2108.06881","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-video-highlight-detection-by","slug":"adaptive-video-highlight-detection-by","title":"Adaptive Video Highlight Detection by Learning from User History","date":"2020-07-19","arxiv_id":"2007.09598","repositories_listed":1,"syntology":null},{"url":"/paper/comprehensive-soccer-video-understanding","slug":"comprehensive-soccer-video-understanding","title":"SoccerDB: A Large-Scale Database for Comprehensive Video Understanding","date":"2019-12-10","arxiv_id":"1912.04465","repositories_listed":1,"syntology":null},{"url":"/paper/single-image-highlight-removal-with-a-sparse","slug":"single-image-highlight-removal-with-a-sparse","title":"Single Image Highlight Removal with a Sparse and Low-Rank Reflection Model","date":"2018-09-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/phd-gifs-personalized-highlight-detection-for","slug":"phd-gifs-personalized-highlight-detection-for","title":"PHD-GIFs: Personalized Highlight Detection for Automatic GIF Creation","date":"2018-04-18","arxiv_id":"1804.06604","repositories_listed":1,"syntology":null},{"url":"/paper/video-highlights-detection-and-summarization-1","slug":"video-highlights-detection-and-summarization-1","title":"Video Highlights Detection and Summarization with Lag-Calibration based on Concept-Emotion Mapping of Crowd-sourced Time-Sync Comments","date":"2017-08-07","arxiv_id":"1708.02210","repositories_listed":1,"syntology":null},{"url":"/paper/aenet-learning-deep-audio-features-for-video","slug":"aenet-learning-deep-audio-features-for-video","title":"AENet: Learning Deep Audio Features for Video Analysis","date":"2017-01-03","arxiv_id":"1701.00599","repositories_listed":1,"syntology":null},{"url":null,"slug":"unsupervised-transcript-assisted-video","title":"Unsupervised Transcript-assisted Video Summarization and Highlight Detection","date":"2025-05-29","arxiv_id":"2505.23268","repositories_listed":0,"syntology":null},{"url":null,"slug":"gameplay-highlights-generation","title":"Gameplay Highlights Generation","date":"2025-05-12","arxiv_id":"2505.07721","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-detection-of-intro-and-credits-in","title":"Automatic Detection of Intro and Credits in Video using CLIP and Multihead Attention","date":"2025-04-13","arxiv_id":"2504.09738","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":"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":"video-llms-for-temporal-reasoning-in-long","title":"Video LLMs for Temporal Reasoning in Long Videos","date":"2024-12-04","arxiv_id":"2412.02930","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":"unsupervised-video-highlight-detection-by","title":"Unsupervised Video Highlight Detection by Learning from Audio and Visual Recurrence","date":"2024-07-18","arxiv_id":"2407.13933","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multimodal-transformer-for-live-streaming","title":"A Multimodal Transformer for Live Streaming Highlight Prediction","date":"2024-06-15","arxiv_id":"2407.12002","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-modality-transferable-video","title":"Unsupervised Modality-Transferable Video Highlight Detection with Representation Activation Sequence Learning","date":"2024-03-14","arxiv_id":"2403.09401","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":"/paper/diffusionvmr-diffusion-model-for-video-moment","slug":"diffusionvmr-diffusion-model-for-video-moment","title":"DiffusionVMR: Diffusion Model for Joint Video Moment Retrieval and Highlight Detection","date":"2023-08-29","arxiv_id":"2308.15109","repositories_listed":0,"syntology":null},{"url":null,"slug":"show-me-what-i-like-detecting-user-specific","title":"Show Me What I Like: Detecting User-Specific Video Highlights Using Content-Based Multi-Head Attention","date":"2022-07-18","arxiv_id":"2207.08352","repositories_listed":0,"syntology":null},{"url":null,"slug":"probing-visual-audio-representation-for-video","title":"Probing Visual-Audio Representation for Video Highlight Detection via Hard-Pairs Guided Contrastive Learning","date":"2022-06-21","arxiv_id":"2206.10157","repositories_listed":0,"syntology":null},{"url":"/paper/0-1-deep-neural-networks-via-block-coordinate","slug":"0-1-deep-neural-networks-via-block-coordinate","title":"0/1 Deep Neural Networks via Block Coordinate Descent","date":"2022-06-19","arxiv_id":"2206.09379","repositories_listed":0,"syntology":null},{"url":null,"slug":"antpivot-livestream-highlight-detection-via","title":"AntPivot: Livestream Highlight Detection via Hierarchical Attention Mechanism","date":"2022-06-10","arxiv_id":"2206.04888","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-pixel-level-distinctions-for-video","title":"Learning Pixel-Level Distinctions for Video Highlight Detection","date":"2022-04-10","arxiv_id":"2204.04615","repositories_listed":0,"syntology":null},{"url":null,"slug":"smart-director-an-event-driven-directing","title":"Smart Director: An Event-Driven Directing System for Live Broadcasting","date":"2022-01-11","arxiv_id":"2201.04024","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-learning-for-unsupervised-video","title":"Contrastive Learning for Unsupervised Video Highlight Detection","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/pr-net-preference-reasoning-for-personalized","slug":"pr-net-preference-reasoning-for-personalized","title":"PR-Net: Preference Reasoning for Personalized Video Highlight Detection","date":"2021-09-04","arxiv_id":"2109.01799","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-task-network-for-joint-specular","title":"A Multi-Task Network for Joint Specular Highlight Detection and Removal","date":"2021-06-19","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"audiovisual-highlight-detection-in-videos","title":"Audiovisual Highlight Detection in Videos","date":"2021-02-11","arxiv_id":"2102.05811","repositories_listed":0,"syntology":null},{"url":null,"slug":"lights-light-specularity-dataset-for-specular","title":"LIGHTS: LIGHT Specularity Dataset for specular detection in Multi-view","date":"2021-01-26","arxiv_id":"2101.10772","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-visual-and-audio-learning-for-video","title":"Joint Visual and Audio Learning for Video Highlight Detection","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-cue-guided-video-highlight-detection","title":"Temporal Cue Guided Video Highlight Detection With Low-Rank Audio-Visual Fusion","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/100000-podcasts-a-spoken-english-document","slug":"100000-podcasts-a-spoken-english-document","title":"100,000 Podcasts: A Spoken English Document Corpus","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/learning-to-detect-specular-highlights-from","slug":"learning-to-detect-specular-highlights-from","title":"Learning to Detect Specular Highlights from Real-world Images","date":"2020-10-10","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mini-net-multiple-instance-ranking-network","title":"MINI-Net: Multiple Instance Ranking Network for Video Highlight Detection","date":"2020-07-20","arxiv_id":"2007.09833","repositories_listed":0,"syntology":null},{"url":null,"slug":"estimating-blink-probability-for-highlight","title":"Estimating Blink Probability for Highlight Detection in Figure Skating Videos","date":"2020-07-02","arxiv_id":"2007.01089","repositories_listed":0,"syntology":null},{"url":null,"slug":"trunet-short-videos-generation-from-long","title":"TruNet: Short Videos Generation from Long Videos via Story-Preserving Truncation","date":"2019-10-14","arxiv_id":"1910.05899","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-multi-stream-highlight-detection","title":"Unsupervised Multi-stream Highlight detection for the Game \"Honor of Kings\"","date":"2019-10-14","arxiv_id":"1910.06189","repositories_listed":0,"syntology":null},{"url":null,"slug":"less-is-more-learning-highlight-detection","title":"Less is More: Learning Highlight Detection from Video Duration","date":"2019-03-03","arxiv_id":"1903.00859","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-unsupervised-multi-view-detection-of","title":"Deep Unsupervised Multi-View Detection of Video Game Stream Highlights","date":"2018-07-25","arxiv_id":"1807.09715","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-ranking-model-for-spatio-temporal","title":"A Deep Ranking Model for Spatio-Temporal Highlight Detection from a 360 Video","date":"2018-01-31","arxiv_id":"1801.10312","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-highlights-detection-and-summarization","title":"Video Highlights Detection and Summarization with Lag-Calibration based on Concept-Emotion Mapping of Crowdsourced Time-Sync Comments","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"highlight-detection-with-pairwise-deep","title":"Highlight Detection With Pairwise Deep Ranking for First-Person Video Summarization","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"discovering-picturesque-highlights-from","title":"Discovering Picturesque Highlights from Egocentric Vacation Videos","date":"2016-01-18","arxiv_id":"1601.04406","repositories_listed":0,"syntology":null}],"syntology_records":18,"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":2,"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/highlight-detection-on-qvhighlights","since_archive":"/sota/highlight-detection-on-qvhighlights#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/highlight-detection-on-tvsum","since_archive":"/sota/highlight-detection-on-tvsum#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":18,"papers_where_code_ran_first_page":"/task/highlight-detection/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/highlight-detection/papers/ran/1","json":"/task/highlight-detection/papers/ran/1.json","rows":18}],"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":"ece0d96800544837d68b9caa2ccefbbbe3df94d6cc1be7300ff91d91f607c9cc","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}