{"url":"/sota/unsupervised-video-summarization-on-tvsum","task":{"name":"Unsupervised Video Summarization","url":"/task/unsupervised-video-summarization","note":null},"dataset":{"name":"TvSum","url":"/dataset/tvsum"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Unsupervised video summarization** approaches overcome the need for ground-truth data (whose production requires time-demanding and laborious manual annotation procedures), based on learning mechanisms that require only an adequately large collection of original videos for their training. Specifically, the training is based on heuristic rules, like the sparsity, the representativeness, and the diversity of the utilized input features/characteristics.","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","Kendall's Tau","Spearman's Rho","training time (s)","Parameters (M)"],"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":"higher","Kendall's Tau":null,"Spearman's Rho":"higher","training time (s)":"lower","Parameters (M)":null}},"counts":{"rows":8,"rows_with_code":7,"rows_with_paper_page":8,"rows_dated":8,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"SegSum","metrics":{"F1-score":"62","Parameters (M)":"5.25"},"uses_additional_data":false,"paper_date":"2025-02-26","paper":"/paper/integrate-the-temporal-scheme-for","paper_url":"https://ieeexplore.ieee.org/document/10904447","paper_title":"Integrate the temporal scheme for unsupervised video summarization via attention mechanism","code":"https://github.com/bavo96/SegSum","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"RS-SUM","metrics":{"F1-score":"61.4","Kendall's Tau":"0.08","Spearman's Rho":"0.106"},"uses_additional_data":false,"paper_date":"2023-09-11","paper":"/paper/adopting-self-supervised-learning-into-1","paper_url":"https://ieeexplore.ieee.org/abstract/document/10222350","paper_title":"Adopting Self-Supervised Learning into Unsupervised Video Summarization through Restorative Score.","code":"https://github.com/mehryar72/RS-SUM","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"AC-SUM-GAN","metrics":{"F1-score":"60.6","Parameters (M)":"26.75","training time (s)":"9380"},"uses_additional_data":false,"paper_date":"2020-11-16","paper":"/paper/ac-sum-gan-connecting-actor-critic-and","paper_url":"https://ieeexplore.ieee.org/document/9259058","paper_title":"AC-SUM-GAN: Connecting Actor-Critic and Generative Adversarial Networks for Unsupervised Video Summarization","code":"https://github.com/e-apostolidis/AC-SUM-GAN","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"CSNet","metrics":{"F1-score":"58.8","Kendall's Tau":"0.025","Parameters (M)":"100.76","Spearman's Rho":"0.034","training time (s)":"1797"},"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":5,"model":"SUM-GAN-sl","metrics":{"F1-score":"58.4","Parameters (M)":"23.31","training time (s)":"3895"},"uses_additional_data":false,"paper_date":"2019-10-21","paper":"/paper/a-stepwise-label-based-approach-for-improving","paper_url":"https://dl.acm.org/doi/abs/10.1145/3347449.3357482","paper_title":"A Stepwise, Label-based Approach for Improving the Adversarial Training in Unsupervised Video Summarization","code":"https://github.com/e-apostolidis/SUM-GAN-sl","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"SUM-GAN-AAE","metrics":{"F1-score":"58.3","Parameters (M)":"24.31","training time (s)":"5423"},"uses_additional_data":false,"paper_date":"2019-12-24","paper":"/paper/unsupervised-video-summarization-via","paper_url":"https://link.springer.com/chapter/10.1007/978-3-030-37731-1_40","paper_title":"Unsupervised Video Summarization via Attention-Driven Adversarial Learning","code":"https://github.com/e-apostolidis/SUM-GAN-AAE","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"DR-DSN","metrics":{"F1-score":"57.6","Kendall's Tau":"0.020","Parameters (M)":"2.63","Spearman's Rho":"0.026","training time (s)":"58.8"},"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":8,"model":"Cycle-SUM","metrics":{"F1-score":"57.6"},"uses_additional_data":false,"paper_date":"2019-04-17","paper":"/paper/cycle-sum-cycle-consistent-adversarial-lstm","paper_url":"http://arxiv.org/abs/1904.08265v1","paper_title":"Cycle-SUM: Cycle-consistent Adversarial LSTM Networks for Unsupervised Video Summarization","code":null,"n_code_links":0,"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":1,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":1,"n_unverified":0,"n_samples":1,"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":1,"n_unverified":0,"n_samples":1,"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"}}}