{"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 (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":76,"tagged_in_all":132,"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/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":5,"n_unverified":8,"n_pointer_only":8}},{"url":"/paper/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","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/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":8,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/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":0,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/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","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","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","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","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/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/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/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","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/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","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","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","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/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","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","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","title":"Language-based Audio Moment Retrieval","date":"2024-09-24","arxiv_id":"2409.15672","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/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","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":9,"n_unverified":4,"n_pointer_only":13}},{"url":"/paper/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_unverified":1,"n_pointer_only":0}}],"syntology_records":13,"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"}}