{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-reinforcement-learning-for-unsupervised","title":"Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward","arxiv_id":"1801.00054","date":"2017-12-29","proceeding":null,"authors":["Kaiyang Zhou","Yu Qiao","Tao Xiang"],"abstract":"Video summarization aims to facilitate large-scale video browsing by\nproducing short, concise summaries that are diverse and representative of\noriginal videos. In this paper, we formulate video summarization as a\nsequential decision-making process and develop a deep summarization network\n(DSN) to summarize videos. DSN predicts for each video frame a probability,\nwhich indicates how likely a frame is selected, and then takes actions based on\nthe probability distributions to select frames, forming video summaries. To\ntrain our DSN, we propose an end-to-end, reinforcement learning-based\nframework, where we design a novel reward function that jointly accounts for\ndiversity and representativeness of generated summaries and does not rely on\nlabels or user interactions at all. During training, the reward function judges\nhow diverse and representative the generated summaries are, while DSN strives\nfor earning higher rewards by learning to produce more diverse and more\nrepresentative summaries. Since labels are not required, our method can be\nfully unsupervised. Extensive experiments on two benchmark datasets show that\nour unsupervised method not only outperforms other state-of-the-art\nunsupervised methods, but also is comparable to or even superior than most of\npublished supervised approaches.","url_abs":"http://arxiv.org/abs/1801.00054v3","url_pdf":"http://arxiv.org/pdf/1801.00054v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-reinforcement-learning-for-unsupervised","repo_url":"https://github.com/KaiyangZhou/vsumm-reinforce","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"deep-reinforcement-learning-for-unsupervised","repo_url":"https://github.com/HoganZhang/pytorch-vsumm-reinforce","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"deep-reinforcement-learning-for-unsupervised","repo_url":"https://github.com/KaiyangZhou/pytorch-vsumm-reinforce","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-for-unsupervised","repo_url":"https://github.com/n9839950/EGH400-2-DSN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"deep-reinforcement-learning-for-unsupervised","repo_url":"https://github.com/neda60/video-summarization-using-FCSN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"deep-reinforcement-learning-for-unsupervised","repo_url":"https://github.com/ymlwww/rlproject","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"sequential-decision-making","task_name":"Sequential Decision Making"},{"task_slug":"supervised-video-summarization","task_name":"Supervised Video Summarization"},{"task_slug":"unsupervised-video-summarization","task_name":"Unsupervised Video Summarization"},{"task_slug":"video-summarization","task_name":"Video Summarization"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/supervised-video-summarization-on-summe","task":"Supervised Video Summarization","dataset":"SumMe","model":"DR-DSN","rank_in_archive_order":20,"of":21,"metrics":{"F1-score (Augmented)":"43.9","F1-score (Canonical)":"42.1"},"uses_additional_data":false},{"leaderboard":"/sota/supervised-video-summarization-on-tvsum","task":"Supervised Video Summarization","dataset":"TvSum","model":"DR-DSN","rank_in_archive_order":20,"of":21,"metrics":{"F1-score (Augmented)":"59.8","F1-score (Canonical)":"58.1"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-video-summarization-on-summe","task":"Unsupervised Video Summarization","dataset":"SumMe","model":"DR-DSN","rank_in_archive_order":10,"of":10,"metrics":{"F1-score":"41.4","Parameters (M)":"2.63","training time (s)":"19.8"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-video-summarization-on-tvsum","task":"Unsupervised Video Summarization","dataset":"TvSum","model":"DR-DSN","rank_in_archive_order":7,"of":8,"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}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1801.00054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.00054"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/KaiyangZhou/vsumm-reinforce","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ymlwww/rlproject","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/KaiyangZhou/pytorch-vsumm-reinforce","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/neda60/video-summarization-using-FCSN","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/n9839950/EGH400-2-DSN","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/HoganZhang/pytorch-vsumm-reinforce","reach":{"status":"unanswered"}}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"c8b52d13ddb9702b","entry":"split_random","repo":"KaiyangZhou/pytorch-vsumm-reinforce","repo_kind":"listed","path":"create_split.py","file_url":"https://github.com/KaiyangZhou/pytorch-vsumm-reinforce/blob/HEAD/create_split.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c8b52d13ddb9702b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}