{"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-highlights-detection-and-summarization-1","title":"Video Highlights Detection and Summarization with Lag-Calibration based on Concept-Emotion Mapping of Crowd-sourced Time-Sync Comments","arxiv_id":"1708.02210","date":"2017-08-07","proceeding":null,"authors":["Qing Ping","Chaomei Chen"],"abstract":"With the prevalence of video sharing, there are increasing demands for\nautomatic video digestion such as highlight detection. Recently, platforms with\ncrowdsourced time-sync video comments have emerged worldwide, providing a good\nopportunity for highlight detection. However, this task is non-trivial: (1)\ntime-sync comments often lag behind their corresponding shot; (2) time-sync\ncomments are semantically sparse and noisy; (3) to determine which shots are\nhighlights is highly subjective. The present paper aims to tackle these\nchallenges by proposing a framework that (1) uses concept-mapped lexical-chains\nfor lag calibration; (2) models video highlights based on comment intensity and\ncombination of emotion and concept concentration of each shot; (3) summarize\neach detected highlight using improved SumBasic with emotion and concept\nmapping. Experiments on large real-world datasets show that our highlight\ndetection method and summarization method both outperform other benchmarks with\nconsiderable margins.","url_abs":"http://arxiv.org/abs/1708.02210v1","url_pdf":"http://arxiv.org/pdf/1708.02210v1.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-highlights-detection-and-summarization-1","repo_url":"https://github.com/ChanningPing/VideoHighlightDetection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"highlight-detection","task_name":"Highlight Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}