{"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":2,"n_unverified":11,"n_pointer_only":13}}},{"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 (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":41,"tagged_in_all":78,"items":[{"url":"/paper/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_unverified":0,"n_pointer_only":1}},{"url":"/paper/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","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":7,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/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":2,"n_unverified":9,"n_pointer_only":11}},{"url":"/paper/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","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","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","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_unverified":2,"n_pointer_only":10}},{"url":"/paper/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":2,"n_unverified":11,"n_pointer_only":13}},{"url":"/paper/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":0,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/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","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":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/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":1,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/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":3,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/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","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":5,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/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":5,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/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":13,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/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":6,"n_unverified":4,"n_pointer_only":10}},{"url":"/paper/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","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":3,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/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","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":11,"n_unverified":6,"n_pointer_only":17}},{"url":"/paper/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_unverified":3,"n_pointer_only":0}},{"url":"/paper/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","title":"UniVTG: Towards Unified Video-Language Temporal Grounding","date":"2023-07-31","arxiv_id":"2307.16715","repositories_listed":1,"syntology":{"n":16,"n_ran":10,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/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","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","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","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_unverified":0,"n_pointer_only":1}}],"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}