{"url":"/sota/moment-retrieval-on-qvhighlights","task":{"name":"Moment Retrieval","url":"/task/moment-retrieval","note":null},"dataset":{"name":"QVHighlights","url":"/dataset/qvhighlights"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"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)","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["mAP","R@1 IoU=0.5","R@1 IoU=0.7","mAP@0.5","mAP@0.75"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"mAP":"higher","R@1 IoU=0.5":"higher","R@1 IoU=0.7":"higher","mAP@0.5":"higher","mAP@0.75":"higher"}},"counts":{"rows":32,"rows_with_code":31,"rows_with_paper_page":31,"rows_dated":31,"rows_using_additional_data":7},"rows":[{"rank_in_archive_order":1,"model":"SG-DETR (w/ PT)","metrics":{"R@1 IoU=0.5":"74.20","R@1 IoU=0.7":"60.40","mAP":"58.80","mAP@0.5":"76.20","mAP@0.75":"60.80"},"uses_additional_data":true,"paper_date":"2024-10-02","paper":"/paper/saliency-guided-detr-for-moment-retrieval-and","paper_url":"https://arxiv.org/abs/2410.01615v1","paper_title":"Saliency-Guided DETR for Moment Retrieval and Highlight Detection","code":"https://github.com/ai-forever/sg-detr","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"SG-DETR","metrics":{"R@1 IoU=0.5":"72.20","R@1 IoU=0.7":"56.60","mAP":"54.10","mAP@0.5":"73.20","mAP@0.75":"55.80"},"uses_additional_data":false,"paper_date":"2024-10-02","paper":"/paper/saliency-guided-detr-for-moment-retrieval-and","paper_url":"https://arxiv.org/abs/2410.01615v1","paper_title":"Saliency-Guided DETR for Moment Retrieval and Highlight Detection","code":"https://github.com/ai-forever/sg-detr","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"LLaVA-MR","metrics":{"R@1 IoU=0.5":"76.59","R@1 IoU=0.7":"61.48","mAP":"52.73","mAP@0.5":"69.41","mAP@0.75":"54.40"},"uses_additional_data":false,"paper_date":"2024-11-21","paper":"/paper/llava-mr-large-language-and-vision-assistant","paper_url":"https://arxiv.org/abs/2411.14505v1","paper_title":"LLaVA-MR: Large Language-and-Vision Assistant for Video Moment Retrieval","code":"https://github.com/swordlidev/LLaVA-MR","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"FlashVTG","metrics":{"R@1 IoU=0.5":"70.69","R@1 IoU=0.7":"53.96","mAP":"52.00","mAP@0.5":"72.33","mAP@0.75":"53.85"},"uses_additional_data":false,"paper_date":"2024-12-18","paper":"/paper/flashvtg-feature-layering-and-adaptive-score","paper_url":"https://arxiv.org/abs/2412.13441v1","paper_title":"FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding","code":"https://github.com/zhuo-cao/flashvtg","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":11,"n_samples":13,"n_pointer_only_licence":13}},{"rank_in_archive_order":5,"model":"InternVideo2-6B","metrics":{"R@1 IoU=0.5":"71.42","R@1 IoU=0.7":"56.45","mAP":"49.24"},"uses_additional_data":true,"paper_date":"2024-03-22","paper":"/paper/internvideo2-scaling-video-foundation-models","paper_url":"https://arxiv.org/abs/2403.15377v4","paper_title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","code":"https://github.com/opengvlab/internvideo","n_code_links":2,"syntology":null},{"rank_in_archive_order":6,"model":"CG-DETR (w/ PT)","metrics":{"R@1 IoU=0.5":"68.48","R@1 IoU=0.7":"53.11","mAP":"47.97","mAP@0.5":"69.40","mAP@0.75":"49.12"},"uses_additional_data":true,"paper_date":"2023-11-15","paper":"/paper/correlation-guided-query-dependency","paper_url":"https://arxiv.org/abs/2311.08835v4","paper_title":"Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding","code":"https://github.com/wjun0830/qd-detr","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":9,"n_samples":11,"n_pointer_only_licence":11}},{"rank_in_archive_order":7,"model":"VideoLights-B-pt","metrics":{"R@1 IoU=0.5":"70.36","R@1 IoU=0.7":"55.25","mAP":"47.94","mAP@0.5":"69.53","mAP@0.75":"49.17"},"uses_additional_data":true,"paper_date":"2024-12-02","paper":"/paper/videolights-feature-refinement-and-cross-task","paper_url":"https://arxiv.org/abs/2412.01558v1","paper_title":"VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrieval","code":"https://github.com/dpaul06/VideoLights","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"LA-DETR","metrics":{"R@1 IoU=0.5":"63.94","R@1 IoU=0.7":"51.10","mAP":"47.93","mAP@0.5":"65.65","mAP@0.75":"49.44"},"uses_additional_data":false,"paper_date":"2024-12-30","paper":"/paper/length-aware-detr-for-robust-moment-retrieval","paper_url":"https://arxiv.org/abs/2412.20816v1","paper_title":"Length-Aware DETR for Robust Moment Retrieval","code":"https://github.com/sjpark5800/la-detr","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"BAM-DETR (w/ audio)","metrics":{"R@1 IoU=0.5":"64.07","R@1 IoU=0.7":"48.12","mAP":"46.91","mAP@0.5":"65.61","mAP@0.75":"47.51"},"uses_additional_data":false,"paper_date":"2023-11-30","paper":"/paper/bam-detr-boundary-aligned-moment-detection","paper_url":"https://arxiv.org/abs/2312.00083v2","paper_title":"BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos","code":"https://github.com/Pilhyeon/BAM-DETR","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":3,"n_samples":11,"n_pointer_only_licence":11}},{"rank_in_archive_order":10,"model":"BAM-DETR (w/ PT ASR Captions)","metrics":{"R@1 IoU=0.5":"63.88","R@1 IoU=0.7":"47.92","mAP":"46.67","mAP@0.5":"66.33","mAP@0.75":"48.22"},"uses_additional_data":true,"paper_date":"2023-11-30","paper":"/paper/bam-detr-boundary-aligned-moment-detection","paper_url":"https://arxiv.org/abs/2312.00083v2","paper_title":"BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos","code":"https://github.com/Pilhyeon/BAM-DETR","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":3,"n_samples":11,"n_pointer_only_licence":11}},{"rank_in_archive_order":11,"model":"LD-DETR","metrics":{"R@1 IoU=0.5":" 66.80","R@1 IoU=0.7":"51.04","mAP":"46.41","mAP@0.5":"67.61","mAP@0.75":" 46.99"},"uses_additional_data":false,"paper_date":"2025-01-18","paper":"/paper/ld-detr-loop-decoder-detection-transformer","paper_url":"https://arxiv.org/abs/2501.10787v1","paper_title":"LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detection","code":"https://github.com/qingchen239/ld-detr","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"R^2-Tuning","metrics":{"R@1 IoU=0.5":"68.03","R@1 IoU=0.7":"49.35","mAP":"46.17","mAP@0.5":"69.04","mAP@0.75":"47.56"},"uses_additional_data":false,"paper_date":"2024-03-31","paper":"/paper/r-2-tuning-efficient-image-to-video-transfer-1","paper_url":"https://arxiv.org/abs/2404.00801v2","paper_title":"$R^2$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding","code":"https://github.com/yeliudev/R2-Tuning","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"BAM-DETR","metrics":{"R@1 IoU=0.5":"62.71","R@1 IoU=0.7":"48.64","mAP":"45.36","mAP@0.5":"64.57","mAP@0.75":"46.33"},"uses_additional_data":false,"paper_date":"2023-11-30","paper":"/paper/bam-detr-boundary-aligned-moment-detection","paper_url":"https://arxiv.org/abs/2312.00083v2","paper_title":"BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos","code":"https://github.com/Pilhyeon/BAM-DETR","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":3,"n_samples":11,"n_pointer_only_licence":11}},{"rank_in_archive_order":14,"model":"video-mamba-suite","metrics":{"R@1 IoU=0.5":"66.65","R@1 IoU=0.7":"52.19","mAP":"45.18","mAP@0.5":"64.37","mAP@0.75":"46.68"},"uses_additional_data":false,"paper_date":"2024-03-14","paper":"/paper/video-mamba-suite-state-space-model-as-a","paper_url":"https://arxiv.org/abs/2403.09626v1","paper_title":"Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding","code":"https://github.com/opengvlab/video-mamba-suite","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":5,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"LLMEPET","metrics":{"R@1 IoU=0.5":"66.73","R@1 IoU=0.7":"49.94","mAP":"44.05","mAP@0.5":"65.76","mAP@0.75":"43.91"},"uses_additional_data":false,"paper_date":"2024-07-21","paper":"/paper/prior-knowledge-integration-via-llm-encoding","paper_url":"https://arxiv.org/abs/2407.15051v3","paper_title":"Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval","code":"https://github.com/fletcherjiang/llmepet","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":6,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"UVCOM (w/ PT ASR Captions)","metrics":{"R@1 IoU=0.5":"64.53","R@1 IoU=0.7":"48.31","mAP":"43.8","mAP@0.5":"64.78","mAP@0.75":"43.65"},"uses_additional_data":true,"paper_date":"2023-11-28","paper":"/paper/bridging-the-gap-a-unified-video","paper_url":"https://arxiv.org/abs/2311.16464v1","paper_title":"Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection","code":"https://github.com/easonxiao-888/uvcom","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"UniVTG (w/ PT)","metrics":{"R@1 IoU=0.5":"65.43","R@1 IoU=0.7":"50.06","mAP":"43.63","mAP@0.5":"64.06","mAP@0.75":"45.02"},"uses_additional_data":true,"paper_date":"2023-07-31","paper":"/paper/univtg-towards-unified-video-language","paper_url":"https://arxiv.org/abs/2307.16715v2","paper_title":"UniVTG: Towards Unified Video-Language Temporal Grounding","code":"https://github.com/showlab/univtg","n_code_links":1,"syntology":{"n_ran":10,"n_unverified":6,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"UVCOM","metrics":{"R@1 IoU=0.5":"63.55","R@1 IoU=0.7":"47.47","mAP":"43.18","mAP@0.5":"63.37","mAP@0.75":"42.67"},"uses_additional_data":false,"paper_date":"2023-11-28","paper":"/paper/bridging-the-gap-a-unified-video","paper_url":"https://arxiv.org/abs/2311.16464v1","paper_title":"Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection","code":"https://github.com/easonxiao-888/uvcom","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"CG-DETR","metrics":{"R@1 IoU=0.5":"65.43","R@1 IoU=0.7":"48.38","mAP":"42.86","mAP@0.5":"64.51","mAP@0.75":"42.77"},"uses_additional_data":false,"paper_date":"2023-11-15","paper":"/paper/correlation-guided-query-dependency","paper_url":"https://arxiv.org/abs/2311.08835v4","paper_title":"Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding","code":"https://github.com/wjun0830/qd-detr","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":9,"n_samples":11,"n_pointer_only_licence":11}},{"rank_in_archive_order":20,"model":"QD-DETR (w/ PT)","metrics":{"R@1 IoU=0.5":"64.1","R@1 IoU=0.7":"46.1","mAP":"40.62","mAP@0.5":"64.3","mAP@0.75":"40.5"},"uses_additional_data":false,"paper_date":"2023-03-24","paper":"/paper/query-dependent-video-representation-for","paper_url":"https://arxiv.org/abs/2303.13874v1","paper_title":"Query-Dependent Video Representation for Moment Retrieval and Highlight Detection","code":"https://github.com/wjun0830/qd-detr","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":21,"model":"QD-DETR (w/ audio)","metrics":{"R@1 IoU=0.5":"63.06","R@1 IoU=0.7":"45.10","mAP":"40.19","mAP@0.5":"63.04","mAP@0.75":"40.10"},"uses_additional_data":false,"paper_date":"2023-03-24","paper":"/paper/query-dependent-video-representation-for","paper_url":"https://arxiv.org/abs/2303.13874v1","paper_title":"Query-Dependent Video Representation for Moment Retrieval and Highlight Detection","code":"https://github.com/wjun0830/qd-detr","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":22,"model":"BM-DETR","metrics":{"R@1 IoU=0.5":"60.12","R@1 IoU=0.7":"43.05","mAP":"40.08","mAP@0.5":"63.08","mAP@0.75":"40.18"},"uses_additional_data":false,"paper_date":"2023-06-05","paper":"/paper/overcoming-weak-visual-textual-alignment-for","paper_url":"https://arxiv.org/abs/2306.02728v3","paper_title":"Background-aware Moment Detection for Video Moment Retrieval","code":"https://github.com/minjoong507/bm-detr","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"QD-DETR (only Video  w/ PT ASR Captions)","metrics":{"R@1 IoU=0.5":"63.2","R@1 IoU=0.7":"45.2","mAP":"40.0","mAP@0.5":"63.4","mAP@0.75":"40.4"},"uses_additional_data":false,"paper_date":"2023-03-24","paper":"/paper/query-dependent-video-representation-for","paper_url":"https://arxiv.org/abs/2303.13874v1","paper_title":"Query-Dependent Video Representation for Moment Retrieval and Highlight Detection","code":"https://github.com/wjun0830/qd-detr","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":24,"model":"QD-DETR (only Video)","metrics":{"R@1 IoU=0.5":"62.40","R@1 IoU=0.7":"44.98","mAP":"39.86","mAP@0.5":"62.52","mAP@0.75":"39.88"},"uses_additional_data":false,"paper_date":"2023-03-24","paper":"/paper/query-dependent-video-representation-for","paper_url":"https://arxiv.org/abs/2303.13874v1","paper_title":"Query-Dependent Video Representation for Moment Retrieval and Highlight Detection","code":"https://github.com/wjun0830/qd-detr","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":25,"model":"UMT (w/ audio + PT ASR Cpations)","metrics":{"mAP":"38.08"},"uses_additional_data":false,"paper_date":"2022-03-23","paper":"/paper/umt-unified-multi-modal-transformers-for","paper_url":"https://arxiv.org/abs/2203.12745v2","paper_title":"UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection","code":"https://github.com/tencentarc/umt","n_code_links":3,"syntology":null},{"rank_in_archive_order":26,"model":"Moment-DETR (w/ PT ASR Cpations)","metrics":{"R@1 IoU=0.5":"59.78","R@1 IoU=0.7":"40.33","mAP":"36.14","mAP@0.5":"60.51","mAP@0.75":"35.36"},"uses_additional_data":false,"paper_date":"2021-07-20","paper":"/paper/qvhighlights-detecting-moments-and-highlights","paper_url":"https://arxiv.org/abs/2107.09609v2","paper_title":"QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries","code":"https://github.com/jayleicn/moment_detr","n_code_links":4,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":1}},{"rank_in_archive_order":27,"model":"UMT","metrics":{"mAP":"36.12"},"uses_additional_data":false,"paper_date":"2022-03-23","paper":"/paper/umt-unified-multi-modal-transformers-for","paper_url":"https://arxiv.org/abs/2203.12745v2","paper_title":"UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection","code":"https://github.com/tencentarc/umt","n_code_links":3,"syntology":null},{"rank_in_archive_order":28,"model":"UniVTG","metrics":{"R@1 IoU=0.5":"58.86","R@1 IoU=0.7":"40.86","mAP":"35.47","mAP@0.5":"57.60","mAP@0.75":"35.59"},"uses_additional_data":false,"paper_date":"2023-07-31","paper":"/paper/univtg-towards-unified-video-language","paper_url":"https://arxiv.org/abs/2307.16715v2","paper_title":"UniVTG: Towards Unified Video-Language Temporal Grounding","code":"https://github.com/showlab/univtg","n_code_links":1,"syntology":{"n_ran":10,"n_unverified":6,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":29,"model":"SeViLA-Localizer","metrics":{"R@1 IoU=0.5":"54.5","R@1 IoU=0.7":"36.5","mAP":"32.3"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":30,"model":"UnLoc-L","metrics":{"R@1 IoU=0.5":"66.1","R@1 IoU=0.7":"46.7"},"uses_additional_data":false,"paper_date":"2023-08-21","paper":"/paper/unloc-a-unified-framework-for-video","paper_url":"https://arxiv.org/abs/2308.11062v1","paper_title":"UnLoc: A Unified Framework for Video Localization Tasks","code":"https://github.com/google-research/scenic","n_code_links":1,"syntology":null},{"rank_in_archive_order":31,"model":"UnLoc-B","metrics":{"R@1 IoU=0.5":"64.5","R@1 IoU=0.7":"48.8"},"uses_additional_data":false,"paper_date":"2023-08-21","paper":"/paper/unloc-a-unified-framework-for-video","paper_url":"https://arxiv.org/abs/2308.11062v1","paper_title":"UnLoc: A Unified Framework for Video Localization Tasks","code":"https://github.com/google-research/scenic","n_code_links":1,"syntology":null},{"rank_in_archive_order":32,"model":"DenoiseLoc","metrics":{"R@1 IoU=0.5":"59.27","R@1 IoU=0.7":"45.07"},"uses_additional_data":false,"paper_date":"2023-04-06","paper":"/paper/boundary-denoising-for-video-activity","paper_url":"https://arxiv.org/abs/2304.02934v1","paper_title":"Boundary-Denoising for Video Activity Localization","code":"https://github.com/frostinassiky/denoiseloc","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,885 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":17,"rows_with_any_sample_ran":17,"distinct_papers_with_graph_line":9,"distinct_papers_with_any_sample_ran":9,"samples_over_distinct_papers":{"n_ran":47,"n_unverified":43,"n_samples":90,"n_pointer_only_licence":37,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":87,"n_unverified":67,"n_samples":154,"n_pointer_only_licence":73,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}