{"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/query-aware-sparse-coding-for-multi-video","title":"Query-Aware Sparse Coding for Multi-Video Summarization","arxiv_id":"1707.04021","date":"2017-07-13","proceeding":null,"authors":["Zhong Ji","Yaru Ma","Yanwei Pang","Xuelong. Li"],"abstract":"Given the explosive growth of online videos, it is becoming increasingly\nimportant to relieve the tedious work of browsing and managing the video\ncontent of interest. Video summarization aims at providing such a technique by\ntransforming one or multiple videos into a compact one. However, conventional\nmulti-video summarization methods often fail to produce satisfying results as\nthey ignore the user's search intent. To this end, this paper proposes a novel\nquery-aware approach by formulating the multi-video summarization in a sparse\ncoding framework, where the web images searched by the query are taken as the\nimportant preference information to reveal the query intent. To provide a\nuser-friendly summarization, this paper also develops an event-keyframe\npresentation structure to present keyframes in groups of specific events\nrelated to the query by using an unsupervised multi-graph fusion method. We\nrelease a new public dataset named MVS1K, which contains about 1, 000 videos\nfrom 10 queries and their video tags, manual annotations, and associated web\nimages. Extensive experiments on MVS1K dataset validate our approaches produce\nsuperior objective and subjective results against several recently proposed\napproaches.","url_abs":"http://arxiv.org/abs/1707.04021v1","url_pdf":"http://arxiv.org/pdf/1707.04021v1.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":[],"tasks":[{"task_slug":"video-summarization","task_name":"Video Summarization"}],"methods":[],"datasets_introduced":[{"slug":"mvs1k","name":"MVS1K","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}