{"url":"/sota/supervised-video-summarization-on-tvsum","task":{"name":"Supervised Video Summarization","url":"/task/supervised-video-summarization","note":null},"dataset":{"name":"TvSum","url":"/dataset/tvsum"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Supervised video summarization** rely on datasets with human-labeled ground-truth annotations (either in the form of video summaries, as in the case of the [SumMe](https://paperswithcode.com/dataset/summe) dataset, or in the form of frame-level importance scores, as in the case of the [TVSum](https://paperswithcode.com/dataset/tvsum-1) dataset), based on which they try to discover the underlying criterion for video frame/fragment selection and video summarization.\r\n\r\nSource: [Video Summarization Using Deep Neural Networks: A Survey](https://arxiv.org/abs/2101.06072)","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":["F1-score (Canonical)","F1-score (Augmented)","Kendall's Tau","Spearman's Rho"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"F1-score (Canonical)":"higher","F1-score (Augmented)":"higher","Kendall's Tau":null,"Spearman's Rho":"higher"}},"counts":{"rows":21,"rows_with_code":17,"rows_with_paper_page":21,"rows_dated":21,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"MAVS [DBLP:conf/mm/FengLKZ18]","metrics":{"F1-score (Canonical)":"67.5"},"uses_additional_data":false,"paper_date":"2021-04-23","paper":"/paper/supervised-video-summarization-via-multiple","paper_url":"https://arxiv.org/abs/2104.11530v2","paper_title":"Supervised Video Summarization via Multiple Feature Sets with Parallel Attention","code":"https://github.com/thswodnjs3/CSTA","n_code_links":3,"syntology":null},{"rank_in_archive_order":2,"model":"CLIP-It","metrics":{"F1-score (Augmented)":"69.0","F1-score (Canonical)":"66.3","Kendall's Tau":"0.108","Spearman's Rho":"0.147"},"uses_additional_data":false,"paper_date":"2021-07-01","paper":"/paper/clip-it-language-guided-video-summarization","paper_url":"https://arxiv.org/abs/2107.00650v2","paper_title":"CLIP-It! Language-Guided Video Summarization","code":"https://github.com/srpkdyy/CLIP-It","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"re-SEQ2SEQ [DBLP:conf/eccv/ZhangGS18]","metrics":{"F1-score (Canonical)":"63.9"},"uses_additional_data":false,"paper_date":"2021-04-23","paper":"/paper/supervised-video-summarization-via-multiple","paper_url":"https://arxiv.org/abs/2104.11530v2","paper_title":"Supervised Video Summarization via Multiple Feature Sets with Parallel Attention","code":"https://github.com/thswodnjs3/CSTA","n_code_links":3,"syntology":null},{"rank_in_archive_order":4,"model":"MC-VSA [DBLP:journals/corr/abs-2006-01410]","metrics":{"F1-score (Canonical)":"63.7"},"uses_additional_data":false,"paper_date":"2021-04-23","paper":"/paper/supervised-video-summarization-via-multiple","paper_url":"https://arxiv.org/abs/2104.11530v2","paper_title":"Supervised Video Summarization via Multiple Feature Sets with Parallel Attention","code":"https://github.com/thswodnjs3/CSTA","n_code_links":3,"syntology":null},{"rank_in_archive_order":5,"model":"iPTNet","metrics":{"F1-score (Augmented)":"64.2","F1-score (Canonical)":"63.4","Kendall's Tau":"0.134","Spearman's Rho":"0.163"},"uses_additional_data":false,"paper_date":"2022-01-01","paper":"/paper/joint-video-summarization-and-moment","paper_url":"http://openaccess.thecvf.com//content/CVPR2022/html/Jiang_Joint_Video_Summarization_and_Moment_Localization_by_Cross-Task_Sample_Transfer_CVPR_2022_paper.html","paper_title":"Joint Video Summarization and Moment Localization by Cross-Task Sample Transfer","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"A2Summ","metrics":{"F1-score (Canonical)":"63.4","Kendall's Tau":"0.137","Spearman's Rho":"0.165"},"uses_additional_data":false,"paper_date":"2023-03-13","paper":"/paper/align-and-attend-multimodal-summarization","paper_url":"https://arxiv.org/abs/2303.07284v3","paper_title":"Align and Attend: Multimodal Summarization with Dual Contrastive Losses","code":"https://github.com/boheumd/A2Summ","n_code_links":2,"syntology":null},{"rank_in_archive_order":7,"model":"RR-STG","metrics":{"F1-score (Augmented)":"63.6","F1-score (Canonical)":"63.0","Kendall's Tau":"0.162","Spearman's Rho":"0.212"},"uses_additional_data":false,"paper_date":"2022-04-06","paper":"/paper/relational-reasoning-over-spatial-temporal","paper_url":"https://ieeexplore.ieee.org/abstract/document/9750933","paper_title":"Relational Reasoning Over Spatial-Temporal Graphs for Video Summarization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"PGL-SUM (maximum learning capacity)","metrics":{"F1-score (Canonical)":"62.7"},"uses_additional_data":false,"paper_date":"2021-12-01","paper":"/paper/combining-global-and-local-attention-with","paper_url":"https://www.iti.gr/~bmezaris/publications/ism2021a_preprint.pdf","paper_title":"Combining Global and Local Attention with Positional Encoding for Video Summarization","code":"https://github.com/e-apostolidis/PGL-SUM","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"DSNet","metrics":{"F1-score (Augmented)":"63.9","F1-score (Canonical)":"62.1"},"uses_additional_data":false,"paper_date":"2020-12-01","paper":"/paper/dsnet-a-flexible-detect-to-summarize-network","paper_url":"https://ieeexplore.ieee.org/document/9275314","paper_title":"DSNet: A Flexible Detect-to-Summarize Network for Video Summarization","code":"https://github.com/li-plus/DSNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"MSVA","metrics":{"F1-score (Canonical)":"61.5","Kendall's Tau":"0.190","Spearman's Rho":"0.210"},"uses_additional_data":false,"paper_date":"2021-04-23","paper":"/paper/supervised-video-summarization-via-multiple","paper_url":"https://arxiv.org/abs/2104.11530v2","paper_title":"Supervised Video Summarization via Multiple Feature Sets with Parallel Attention","code":"https://github.com/thswodnjs3/CSTA","n_code_links":3,"syntology":null},{"rank_in_archive_order":11,"model":"DMASum","metrics":{"F1-score (Canonical)":"61.4","Kendall's Tau":"0.203","Spearman's Rho":"0.267"},"uses_additional_data":false,"paper_date":"2020-08-19","paper":"/paper/query-twice-dual-mixture-attention-meta","paper_url":"https://arxiv.org/abs/2008.08360v1","paper_title":"Query Twice: Dual Mixture Attention Meta Learning for Video Summarization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"PGL-SUM","metrics":{"F1-score (Canonical)":"61.0","Kendall's Tau":"0.157","Spearman's Rho":"0.206"},"uses_additional_data":false,"paper_date":"2021-12-01","paper":"/paper/combining-global-and-local-attention-with","paper_url":"https://www.iti.gr/~bmezaris/publications/ism2021a_preprint.pdf","paper_title":"Combining Global and Local Attention with Positional Encoding for Video Summarization","code":"https://github.com/e-apostolidis/PGL-SUM","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"M-AVS [DBLP:journals/corr/abs-1708-09545]","metrics":{"F1-score (Canonical)":"61"},"uses_additional_data":false,"paper_date":"2021-04-23","paper":"/paper/supervised-video-summarization-via-multiple","paper_url":"https://arxiv.org/abs/2104.11530v2","paper_title":"Supervised Video Summarization via Multiple Feature Sets with Parallel Attention","code":"https://github.com/thswodnjs3/CSTA","n_code_links":3,"syntology":null},{"rank_in_archive_order":14,"model":"VJMHT","metrics":{"F1-score (Augmented)":"61.9","F1-score (Canonical)":"60.9","Kendall's Tau":"0.097","Spearman's Rho":"0.105"},"uses_additional_data":false,"paper_date":"2021-12-27","paper":"/paper/video-joint-modelling-based-on-hierarchical","paper_url":"https://arxiv.org/abs/2112.13478v2","paper_title":"Video Joint Modelling Based on Hierarchical Transformer for Co-summarization","code":"https://github.com/thswodnjs3/CSTA","n_code_links":2,"syntology":null},{"rank_in_archive_order":15,"model":"SSPVS(+Text)","metrics":{"F1-score (Canonical)":"60.4","Kendall's Tau":"0.181","Spearman's Rho":"0.238"},"uses_additional_data":false,"paper_date":"2022-01-07","paper":"/paper/video-summarization-based-on-video-text","paper_url":"https://arxiv.org/abs/2201.02494v4","paper_title":"Progressive Video Summarization via Multimodal Self-supervised Learning","code":"https://github.com/thswodnjs3/CSTA","n_code_links":2,"syntology":null},{"rank_in_archive_order":16,"model":"SSPVS","metrics":{"F1-score (Augmented)":"61.8","F1-score (Canonical)":"60.3","Kendall's Tau":"0.177","Spearman's Rho":"0.233"},"uses_additional_data":false,"paper_date":"2022-01-07","paper":"/paper/video-summarization-based-on-video-text","paper_url":"https://arxiv.org/abs/2201.02494v4","paper_title":"Progressive Video Summarization via Multimodal Self-supervised Learning","code":"https://github.com/thswodnjs3/CSTA","n_code_links":2,"syntology":null},{"rank_in_archive_order":17,"model":"HMT","metrics":{"F1-score (Augmented)":"60.3","F1-score (Canonical)":"60.1","Kendall's Tau":"0.096","Spearman's Rho":"0.107"},"uses_additional_data":false,"paper_date":"2021-09-22","paper":"/paper/hierarchical-multimodal-transformer-to","paper_url":"https://arxiv.org/abs/2109.10559v1","paper_title":"Hierarchical Multimodal Transformer to Summarize Videos","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":18,"model":"VASNet [DBLP:conf/accv/FajtlSAMR18]","metrics":{"F1-score (Canonical)":"59.8"},"uses_additional_data":false,"paper_date":"2021-04-23","paper":"/paper/supervised-video-summarization-via-multiple","paper_url":"https://arxiv.org/abs/2104.11530v2","paper_title":"Supervised Video Summarization via Multiple Feature Sets with Parallel Attention","code":"https://github.com/thswodnjs3/CSTA","n_code_links":3,"syntology":null},{"rank_in_archive_order":19,"model":"CSNet","metrics":{"F1-score (Augmented)":"57.1","F1-score (Canonical)":"58.5"},"uses_additional_data":false,"paper_date":"2018-11-24","paper":"/paper/discriminative-feature-learning-for","paper_url":"http://arxiv.org/abs/1811.09791v1","paper_title":"Discriminative Feature Learning for Unsupervised Video Summarization","code":"https://github.com/wildoctopus/SADNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"DR-DSN","metrics":{"F1-score (Augmented)":"59.8","F1-score (Canonical)":"58.1"},"uses_additional_data":false,"paper_date":"2017-12-29","paper":"/paper/deep-reinforcement-learning-for-unsupervised","paper_url":"http://arxiv.org/abs/1801.00054v3","paper_title":"Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward","code":"https://github.com/KaiyangZhou/pytorch-vsumm-reinforce","n_code_links":6,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":21,"model":"CSTA","metrics":{"Kendall's Tau":"0.194","Spearman's Rho":"0.255"},"uses_additional_data":false,"paper_date":"2024-05-20","paper":"/paper/csta-cnn-based-spatiotemporal-attention-for","paper_url":"https://arxiv.org/abs/2405.11905v2","paper_title":"CSTA: CNN-based Spatiotemporal Attention for Video Summarization","code":"https://github.com/thswodnjs3/CSTA","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":1,"n_samples":8,"n_pointer_only_licence":0}}],"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":2,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":8,"n_unverified":1,"n_samples":9,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":8,"n_unverified":1,"n_samples":9,"n_pointer_only_licence":0,"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"}}}