{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/discriminative-feature-learning-for","title":"Discriminative Feature Learning for Unsupervised Video Summarization","arxiv_id":"1811.09791","date":"2018-11-24","proceeding":null,"authors":["Yunjae Jung","Donghyeon Cho","Dahun Kim","Sanghyun Woo","In So Kweon"],"abstract":"In this paper, we address the problem of unsupervised video summarization\nthat automatically extracts key-shots from an input video. Specifically, we\ntackle two critical issues based on our empirical observations: (i) Ineffective\nfeature learning due to flat distributions of output importance scores for each\nframe, and (ii) training difficulty when dealing with long-length video inputs.\nTo alleviate the first problem, we propose a simple yet effective\nregularization loss term called variance loss. The proposed variance loss\nallows a network to predict output scores for each frame with high discrepancy\nwhich enables effective feature learning and significantly improves model\nperformance. For the second problem, we design a novel two-stream network named\nChunk and Stride Network (CSNet) that utilizes local (chunk) and global\n(stride) temporal view on the video features. Our CSNet gives better\nsummarization results for long-length videos compared to the existing methods.\nIn addition, we introduce an attention mechanism to handle the dynamic\ninformation in videos. We demonstrate the effectiveness of the proposed methods\nby conducting extensive ablation studies and show that our final model achieves\nnew state-of-the-art results on two benchmark datasets.","url_abs":"http://arxiv.org/abs/1811.09791v1","url_pdf":"http://arxiv.org/pdf/1811.09791v1.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":"discriminative-feature-learning-for","repo_url":"https://github.com/wildoctopus/SADNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"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"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/supervised-video-summarization-on-summe","task":"Supervised Video Summarization","dataset":"SumMe","model":"CSNet","rank_in_archive_order":14,"of":21,"metrics":{"F1-score (Augmented)":"48.7","F1-score (Canonical)":"48.6"},"uses_additional_data":false},{"leaderboard":"/sota/supervised-video-summarization-on-tvsum","task":"Supervised Video Summarization","dataset":"TvSum","model":"CSNet","rank_in_archive_order":19,"of":21,"metrics":{"F1-score (Augmented)":"57.1","F1-score (Canonical)":"58.5"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-video-summarization-on-summe","task":"Unsupervised Video Summarization","dataset":"SumMe","model":"CSNet","rank_in_archive_order":4,"of":10,"metrics":{"F1-score":"51.3","Parameters (M)":"100.76","training time (s)":"568.6"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-video-summarization-on-tvsum","task":"Unsupervised Video Summarization","dataset":"TvSum","model":"CSNet","rank_in_archive_order":4,"of":8,"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}],"syntology":{"syntology_url":"https://syntology.ai/paper/1811.09791","atlas_url":"https://app.syntology.ai/?focus=1811.09791","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1811.09791"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1811.09791\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1811.09791"},"call":"get_concepts_for_paper(arxiv_id=\"1811.09791\")"}],"by_repo":[{"repo":"wildoctopus/SADNet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"923ecbcd97753122e70249c8152583313483cbf5f9a427d9876f26179405d65b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}