{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T19:54:59Z","timestamp":1760385299311,"version":"3.40.4"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2013,11,1]],"date-time":"2013-11-01T00:00:00Z","timestamp":1383264000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2013,11,1]],"date-time":"2013-11-01T00:00:00Z","timestamp":1383264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2013,11,1]],"date-time":"2013-11-01T00:00:00Z","timestamp":1383264000000},"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":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2013,11]]},"DOI":"10.1109\/tmm.2013.2266635","type":"journal-article","created":{"date-parts":[[2013,6,6]],"date-time":"2013-06-06T18:11:02Z","timestamp":1370542262000},"page":"1543-1552","source":"Crossref","is-referenced-by-count":45,"title":["Face Expression Recognition by Cross Modal Data Association"],"prefix":"10.1109","volume":"15","author":[{"given":"Ashish","family":"Tawari","sequence":"first","affiliation":[{"name":"Computer Vision and Robotics Research Laboratory, University of California, San Diego, La Jolla, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohan Manubhai","family":"Trivedi","sequence":"additional","affiliation":[{"name":"Computer Vision and Robotics Research Laboratory, University of California, San Diego, La Jolla, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-009-0344-2"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"435","DOI":"10.1007\/978-3-540-92892-8_44","volume":"5371","author":"paleari","year":"2009","journal-title":"Advances in Multimedia Modeling"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.1132"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2011.5771416"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1007\/978-3-540-69905-7_27","article-title":"Blur insensitive texture classification using local phase quantization","volume":"5099","author":"ojansivu","year":"2008","journal-title":"Image and Signal Processing"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2002.1017623"},{"journal-title":"Data Mining Practical Machine Learning Tools and Techniques Second Edition (Morgan Kaufmann Series in Data Management Systems)","year":"2005","author":"witten","key":"ref37"},{"key":"ref36","first-page":"8","article-title":"The enterface'05 audiovisual emotion database","author":"martin","year":"2006","journal-title":"Proc 21st Int Conf Data Engineering Workshops"},{"key":"ref35","first-page":"97","article-title":"Accurate short-term analysis of the fundamental frequency and the harmonics-to-noise ratio of a sampled sound","author":"paul","year":"1993","journal-title":"Inst Phonet Sci 17"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2010.5547956"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334688"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1007\/978-3-642-15760-8_35","volume":"6231","author":"gaj?ek","year":"2010","journal-title":"Text Speech and Dialogue"},{"key":"ref11","first-page":"81","article-title":"Manifold based analysis of facial expression","author":"hu","year":"2004","journal-title":"Proc Conf Computer Vision and Pattern Recognition Workshop"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.5772\/4841"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.457"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1110"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.297"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2010.5543267"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2011.5771364"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2011.5771374"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/S1077-3142(03)00081-X"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2057231"},{"key":"ref28","article-title":"Audio-visual data association for face expression analysis","author":"tawari","year":"2012","journal-title":"Proc Int Conf Pattern Recognition"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2009.2026675"},{"key":"ref27","first-page":"877","article-title":"Audio-visual based emotion recognition using tripled hidden Markov model","volume":"5","author":"song","year":"2004","journal-title":"Proc IEEE Int Conf Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3758\/BF03206096"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459377"},{"key":"ref5","article-title":"Audio-visual speech recognition","author":"neti","year":"2000","journal-title":"Final Workshop 2000 Report"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2058095"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1111\/j.0963-7214.2004.01502010.x"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2010.2044241"},{"journal-title":"Affective Computing","year":"1997","author":"picard","key":"ref1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.52"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/AFGR.2000.840611"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1142\/S021969130400041X"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1007\/0-387-27257-7_12","author":"tian","year":"2005","journal-title":"Handbook of Face Recognition"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2212776.2223786"},{"key":"ref24","first-page":"58","article-title":"Semantic audio-visual data fusion for automatic emotion recognition","author":"datcu","year":"2008","journal-title":"Proc Euromedia'2008 Porto"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2011.6033615"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/AFGR.2004.1301585"},{"key":"ref26","first-page":"967","article-title":"Audio-visual affect recognition through multi-stream fused hmm for hci","volume":"2","author":"zeng","year":"2005","journal-title":"Proc IEEE Computer Society Conf Computer Vision and Pattern Recognition"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.927665"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/6630084\/06525327.pdf?arnumber=6525327","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T17:41:58Z","timestamp":1745343718000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6525327\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,11]]},"references-count":42,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2013.2266635","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2013,11]]}}}