{"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/video-summarization-with-long-short-term","title":"Video Summarization with Long Short-term Memory","arxiv_id":"1605.08110","date":"2016-05-26","proceeding":null,"authors":["Ke Zhang","Wei-Lun Chao","Fei Sha","Kristen Grauman"],"abstract":"We propose a novel supervised learning technique for summarizing videos by\nautomatically selecting keyframes or key subshots. Casting the problem as a\nstructured prediction problem on sequential data, our main idea is to use Long\nShort-Term Memory (LSTM), a special type of recurrent neural networks to model\nthe variable-range dependencies entailed in the task of video summarization.\nOur learning models attain the state-of-the-art results on two benchmark video\ndatasets. Detailed analysis justifies the design of the models. In particular,\nwe show that it is crucial to take into consideration the sequential structures\nin videos and model them. Besides advances in modeling techniques, we introduce\ntechniques to address the need of a large number of annotated data for training\ncomplex learning models. There, our main idea is to exploit the existence of\nauxiliary annotated video datasets, albeit heterogeneous in visual styles and\ncontents. Specifically, we show domain adaptation techniques can improve\nsummarization by reducing the discrepancies in statistical properties across\nthose datasets.","url_abs":"http://arxiv.org/abs/1605.08110v2","url_pdf":"http://arxiv.org/pdf/1605.08110v2.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":"video-summarization-with-long-short-term","repo_url":"https://github.com/kezhang-cs/Video-Summarization-with-LSTM","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"structured-prediction","task_name":"Structured Prediction"},{"task_slug":"video-summarization","task_name":"Video Summarization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1605.08110","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}