{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T18:17:42Z","timestamp":1769537862588,"version":"3.49.0"},"reference-count":10,"publisher":"IEEE","license":[{"start":{"date-parts":[[2004,1,1]],"date-time":"2004-01-01T00:00:00Z","timestamp":1072915200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2004,1,1]],"date-time":"2004-01-01T00:00:00Z","timestamp":1072915200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2004]]},"DOI":"10.1109\/icarcv.2004.1469078","type":"proceedings-article","created":{"date-parts":[[2005,7,27]],"date-time":"2005-07-27T13:52:28Z","timestamp":1122472348000},"page":"1533-1537 Vol. 2","source":"Crossref","is-referenced-by-count":0,"title":["Efficient identification of speakers in news video based on shot segmentation"],"prefix":"10.1109","author":[{"family":"Qing Chang","sequence":"first","affiliation":[{"name":"Dept. of Comput. Sci. & Eng., Fudan Univ., Shanghai, China"}]},{"family":"Xiang-yang Xue","sequence":"additional","affiliation":[{"name":"Dept. of Comput. Sci. & Eng., Fudan Univ., Shanghai, China"}]},{"family":"Hong Lu","sequence":"additional","affiliation":[{"name":"Dept. of Comput. Sci. & Eng., Fudan Univ., Shanghai, China"}]},{"family":"You-san Nie","sequence":"additional","affiliation":[{"name":"Dept. of Comput. Sci. & Eng., Fudan Univ., Shanghai, China"}]}],"member":"263","reference":[{"key":"3","first-page":"1998","article-title":"Exploring video structure beyond the shots","author":"rui","year":"0","journal-title":"IEEE International Conference on Multimedia Computing and Systems"},{"key":"2","article-title":"Audiovisual based adaptive speaker identification","volume":"5","author":"li","year":"2003","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing 2003"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1109\/79.317924"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1145\/641007.641127"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.804546"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.596192"},{"key":"5","article-title":"Compressed domain video segmentation","volume":"cs tr 3688","author":"kobla","year":"0","journal-title":"CfAR Technical Report"},{"key":"4","doi-asserted-by":"crossref","DOI":"10.1007\/s005300050138","article-title":"Table of content analysis in videos","author":"rui","year":"1999","journal-title":"ACM Journal of Multimedia systems"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/89.365379"},{"key":"8","first-page":"205","article-title":"Automatic musical genre classification of audio signals","author":"tzanetakis","year":"2001","journal-title":"Proc Int Symposium on Music Inform Retriev (ISMIR)"}],"event":{"name":"2004 8th International Conference on Control, Automation, Robotics and Vision (ICARCV)","location":"Kunming, China","start":{"date-parts":[[2004,12,6]]},"end":{"date-parts":[[2004,12,9]]}},"container-title":["ICARCV 2004 8th Control, Automation, Robotics and Vision Conference, 2004."],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/9908\/31512\/01469078.pdf?arnumber=1469078","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T05:40:46Z","timestamp":1769492446000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/1469078\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2004]]},"references-count":10,"URL":"https:\/\/doi.org\/10.1109\/icarcv.2004.1469078","relation":{},"subject":[],"published":{"date-parts":[[2004]]}}}