{"url":"/task/natural-language-moment-retrieval","name":"Natural Language Moment Retrieval","slug":"natural-language-moment-retrieval","description_markdown":null,"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":22,"papers_with_code":21,"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":5,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/natural-language-moment-retrieval-on-tacos","slug":"natural-language-moment-retrieval-on-tacos","dataset":"TACoS","dataset_url":"/dataset/tacos-multi-level-corpus","rows_in_archive":13,"metrics":["R@1,IoU=0.3","R@1,IoU=0.5","R@1,IoU=0.7","R@5,IoU=0.1","R@5,IoU=0.3","R@5,IoU=0.5","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}},{"leaderboard":"/sota/natural-language-moment-retrieval-on","slug":"natural-language-moment-retrieval-on","dataset":"ActivityNet Captions","dataset_url":"/dataset/activitynet-captions","rows_in_archive":8,"metrics":["R@1,IoU=0.5","R@1,IoU=0.7","R@5,IoU=0.5","R@5,IoU=0.7"],"first_row_in_archive_order":{"model":"GVL (paragraph-level)","paper_title":"Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos","paper_url":"/paper/learning-grounded-vision-language","paper_date":"2023-03-11","arxiv_id":"2303.06378","code_links":[{"title":"zjr2000/gvl","url":"https://github.com/zjr2000/gvl"}],"syntology":{"n":12,"n_ran":1,"n_unverified":11,"n_pointer_only":0}}},{"leaderboard":"/sota/natural-language-moment-retrieval-on-mad","slug":"natural-language-moment-retrieval-on-mad","dataset":"MAD","dataset_url":"/dataset/mad","rows_in_archive":8,"metrics":["R@1,IoU=0.1","R@1,IoU=0.3","R@1,IoU=0.5","R@10,IoU=0.1","R@10,IoU=0.3","R@10,IoU=0.5","R@100,IoU=0.1","R@100,IoU=0.3","R@100,IoU=0.5","R@5,IoU=0.1","R@5,IoU=0.5","R@50,IoU=0.1","R@50,IoU=0.3","R@50,IoU=0.5","R@5,IoU=0.3"],"first_row_in_archive_order":{"model":"ReVisionLLM","paper_title":"ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos","paper_url":"/paper/revisionllm-recursive-vision-language-model","paper_date":"2024-11-22","arxiv_id":"2411.14901","code_links":[{"title":"tanveer81/revisionllm","url":"https://github.com/tanveer81/revisionllm"}],"syntology":null}},{"leaderboard":"/sota/natural-language-moment-retrieval-on-didemo","slug":"natural-language-moment-retrieval-on-didemo","dataset":"DiDeMo","dataset_url":"/dataset/didemo","rows_in_archive":1,"metrics":["R@1,IoU=0.5","R@1,IoU=0.7","R@1,IoU=1.0","R@5,IoU=0.5","R@5,IoU=0.7","R@5,IoU=1.0"],"first_row_in_archive_order":{"model":"VLG-Net","paper_title":"VLG-Net: Video-Language Graph Matching Network for Video Grounding","paper_url":"/paper/vlg-net-video-language-graph-matching-network","paper_date":"2020-11-19","arxiv_id":"2011.10132","code_links":[{"title":"Soldelli/VLG-Net","url":"https://github.com/Soldelli/VLG-Net"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/activitynet-captions","name":"ActivityNet Captions","full_name":"","num_papers_in_archive":255},{"url":"/dataset/didemo","name":"DiDeMo","full_name":"Distinct Describable Moments","num_papers_in_archive":216},{"url":"/dataset/tacos-multi-level-corpus","name":"TACoS Multi-Level Corpus","full_name":"","num_papers_in_archive":45},{"url":"/dataset/mad","name":"MAD","full_name":"","num_papers_in_archive":36},{"url":"/dataset/longvale","name":"LongVALE","full_name":"","num_papers_in_archive":2}],"subtasks":[],"parent_tasks":[{"url":"/task/video","name":"Video"}],"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":21,"of":21,"tagged_in_all":22,"items":[{"url":"/paper/rgnet-a-unified-retrieval-and-grounding","title":"RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos","date":"2023-12-11","arxiv_id":"2312.06729","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/decafnet-delegate-and-conquer-for-efficient","title":"DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos","date":"2025-05-22","arxiv_id":"2505.16376","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/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/revisionllm-recursive-vision-language-model","title":"ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos","date":"2024-11-22","arxiv_id":"2411.14901","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/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/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/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}},{"url":"/paper/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/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":8,"n_unverified":3,"n_pointer_only":11}},{"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/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/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/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/learning-grounded-vision-language","title":"Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos","date":"2023-03-11","arxiv_id":"2303.06378","repositories_listed":1,"syntology":{"n":12,"n_ran":1,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/localizing-moments-in-long-video-via","title":"Localizing Moments in Long Video Via Multimodal Guidance","date":"2023-02-26","arxiv_id":"2302.13372","repositories_listed":1,"syntology":null},{"url":"/paper/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_unverified":0,"n_pointer_only":1}},{"url":"/paper/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_unverified":0,"n_pointer_only":0}},{"url":"/paper/dense-regression-network-for-video-grounding","title":"Dense Regression Network for Video Grounding","date":"2020-04-07","arxiv_id":"2004.03545","repositories_listed":1,"syntology":null}],"syntology_records":10,"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"}}