{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T14:05:54Z","timestamp":1774533954986,"version":"3.50.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2015,6,1]],"date-time":"2015-06-01T00:00:00Z","timestamp":1433116800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2015,6]]},"DOI":"10.1109\/taslp.2014.2387411","type":"journal-article","created":{"date-parts":[[2015,1,5]],"date-time":"2015-01-05T19:24:56Z","timestamp":1420485896000},"page":"1031-1041","source":"Crossref","is-referenced-by-count":13,"title":["Audio-Based Video Genre Identification"],"prefix":"10.1109","volume":"23","author":[{"given":"Mickael","family":"Rouvier","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stanislas","family":"Oger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georges","family":"Linares","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Driss","family":"Matrouf","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bernard","family":"Merialdo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingbo","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"404","author":"bay","year":"2006","journal-title":"Computer Vision and Image Understanding (CVIU)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCIMA.2007.152"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1877850.1877858"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2008.919173"},{"key":"ref30","article-title":"Implementation of a fast artificial neural network library","author":"nissen","year":"2003"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011139631724"},{"key":"ref36","volume":"1","author":"manjunath","year":"2002","journal-title":"Introduction to MPEG-7 Multimedia Content Description Interface"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941230"},{"key":"ref34","article-title":"Video classification based on HMM using text and faces","author":"dimitrova","year":"2000","journal-title":"Proc Eur Signal Process Conf (EUSIPCO)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.608002"},{"key":"ref11","article-title":"Overview of mediaeval 2011rich speech retrieval task and genre tagging task","author":"larson","year":"2011","journal-title":"Proc MediaEval ?11"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"ref12","article-title":"Lia@mediaeval 2011: Compact representation of heterogeneous descriptors for video genre classification","author":"rouvier","year":"2011","journal-title":"Proc MediaEval ?11"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CBMI.2014.6849847"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1155\/S1110865704310024","article-title":"A tutorial on text-independent speaker verification","author":"bimbot","year":"2004","journal-title":"EURASIP J Appl Signal Process Spec Iss Biometric Signal Process"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/89.279278"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0361"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2006.870086"},{"key":"ref18","article-title":"Factor analysis for audio-based video genre classification","author":"rouvier","year":"2009","journal-title":"Proc Int Conf Speech Commun Technol"},{"key":"ref19","article-title":"Broadcast news speaker tracking for ester 2005 campaign","author":"scheffer","year":"2005","journal-title":"Proc Int Conf Speech Commun Technol"},{"key":"ref28","article-title":"Robust audio-based classification of video genre","author":"rouvier","year":"2009","journal-title":"Proc Int Conf Speech Commun Technol"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2002.1048494"},{"key":"ref27","first-page":"1289","article-title":"An extensive empirical study of feature selection metrics for text classification","volume":"3","author":"forman","year":"2003","journal-title":"J Mach Learn Res (JMLR)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30499-9_111"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68585-2_32"},{"key":"ref29","article-title":"Icsiboost","author":"favre","year":"2007"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2001.1237850"},{"key":"ref8","article-title":"Video classification using spatial-temporal features and pca","author":"xu","year":"2003","journal-title":"Proc Int Conf Multimedia and Expo (ICME)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/EURMIC.2001.952477"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/ima.20150"},{"key":"ref1","article-title":"Classification of non-edited broadcast video using holistic low-level features","author":"xu","year":"2002","journal-title":"Int Workshop Distributed Computing (IWDC)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2003.1221586"},{"key":"ref20","article-title":"Combining speaker identification and bic for speaker diarization","author":"zhu","year":"2005","journal-title":"Proc Int Conf Speech Commun Technol"},{"key":"ref46","author":"m\ufffdenp\ufffd\ufffd","year":"2003","journal-title":"The Local Binary Pattern Approach to Texture Analysis Extensions and Applications"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/357744.357758"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.1999-176x","article-title":"Speech\/music discrimination based on posterior probability features","author":"williams","year":"1999","journal-title":"Proc Int Conf Speech Commun Technol"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74628-7_40"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/0031-3203(95)00067-4"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/641007.641075"},{"key":"ref42","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Adv Neural Inf Process Syst (NIPS)"},{"key":"ref23","article-title":"Using closed captions and visual features to classify movies by genre","author":"brezeale","year":"2006","journal-title":"Proc Int Workshop Multimedia Data Mining KDD (MDM\/KDD)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383266"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809071"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2008.2001050"},{"key":"ref25","first-page":"33","article-title":"Text categorization based on weighted inverse document frequency","author":"tokunaga","year":"1994","journal-title":"Special Interest Groups Inf Process Soc Jpn (SIG-IPSJ)"},{"key":"ref43","article-title":"Similarity of color images","author":"stricker","year":"1995","journal-title":"Proc Soc Photo-Opt Instrum Eng (SPIE)"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7084230\/07001198.pdf?arnumber=7001198","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T00:18:00Z","timestamp":1747354680000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7001198\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,6]]},"references-count":47,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2014.2387411","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,6]]}}}