{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T14:40:07Z","timestamp":1782312007700,"version":"3.54.5"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2013,6,1]],"date-time":"2013-06-01T00:00:00Z","timestamp":1370044800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/Crown.html"},{"start":{"date-parts":[[2013,6,1]],"date-time":"2013-06-01T00:00:00Z","timestamp":1370044800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/Crown.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2013,6]]},"DOI":"10.1109\/tmm.2013.2238522","type":"journal-article","created":{"date-parts":[[2013,1,9]],"date-time":"2013-01-09T22:36:44Z","timestamp":1357771004000},"page":"884-897","source":"Crossref","is-referenced-by-count":26,"title":["Learning a Contextual Multi-Thread Model for Movie\/TV Scene Segmentation"],"prefix":"10.1109","volume":"15","author":[{"given":"Cailiang","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.876299"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2006.888023"},{"key":"ref33","first-page":"227","article-title":"Detection of documentary scene changes by audio-visual fusion","author":"velivelli","year":"2004","journal-title":"Proc ACM Int Conf Image Video Retrieval"},{"key":"ref32","first-page":"1453","article-title":"Large margin methods for structured and interdependent output variables","volume":"6","author":"tsochantaridis","year":"2005","journal-title":"J Mach Learning Res"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2004.830810"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1109\/ICME.2000.871563","article-title":"Video scene segmentation using video and audio features","volume":"2","author":"sundaram","year":"2000","journal-title":"Proc IEEE Int Conf Multimedia Expo"},{"key":"ref37","first-page":"399","article-title":"Video browsing using clustering and scene transitions on compressed sequences","volume":"2417","author":"yeung","year":"1995","journal-title":"Multimedia Computing and Networking"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1006\/cviu.1997.0628"},{"key":"ref35","first-page":"2","article-title":"Discriminative genre-independent audio-visual scene change detection","volume":"7255","author":"wilson","year":"2009","journal-title":"Proc SPIE Conf on Storage & Retrieval for Image and Video Databases"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972757.25"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/BF01890115"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383489"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","article-title":"Maximum likelihood from incomplete data via the EM algorithm","volume":"39","author":"dempster","year":"1977","journal-title":"J Roy Statist Soc B"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2007.4284704"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/76.767124"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1998.698632"},{"key":"ref15","first-page":"282","article-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","author":"lafferty","year":"2001","journal-title":"Proc IEEE Int Conf Mach Learning"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(90)90025-5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995681"},{"key":"ref18","first-page":"917","article-title":"A novel role-based movie scene segmentation method","author":"liang","year":"2009","journal-title":"Proc IEEE Pacific Rim Conf Multimedia"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MMCS.1999.779282"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s005300050138"},{"key":"ref4","author":"bordwell","year":"2001","journal-title":"Film Art An Introduction"},{"key":"ref27","first-page":"124","article-title":"Video scene determination using audiovisual data analysis","author":"rho","year":"2004","journal-title":"Proc Int Conf Distrib Comput Syst Workshops"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177699147"},{"key":"ref6","first-page":"33","article-title":"Statistical techniques for natural language parsing","volume":"18","author":"charniak","year":"1997","journal-title":"AI Mag"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2011.2138830"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1007\/3-540-45113-7_44","article-title":"Audio-assisted scene segmentation for story browsing","author":"cao","year":"2003","journal-title":"Proc ACM Int Conf Image and Video Retrieval"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2002.1035606"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.2008924"},{"key":"ref2","first-page":"561","article-title":"Support vector machines for multiple-instance learning","author":"andrews","year":"2003","journal-title":"Adv Neural Inf Proc Syst"},{"key":"ref9","first-page":"158","article-title":"Movie\/script: Alignment and parsing of video and text transcription","author":"cour","year":"2008","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref1","year":"0"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-011-5014-9_12"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2010.17"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2005.1465515"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1199538"},{"key":"ref41","first-page":"229","article-title":"Scene change detection based on audio and video content analysis","author":"zhu","year":"2003","journal-title":"Proc 4th Int Conf Comput Intell and Multimedia Appl"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/11590064_25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2005.858392"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587635"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6046\/6515699\/06408283.pdf?arnumber=6408283","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,4]],"date-time":"2024-05-04T14:44:55Z","timestamp":1714833895000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6408283\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,6]]},"references-count":41,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2013.2238522","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,6]]}}}