{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:07:36Z","timestamp":1775837256946,"version":"3.50.1"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2018,10,1]],"date-time":"2018-10-01T00:00:00Z","timestamp":1538352000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61572050"],"award-info":[{"award-number":["61572050"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["LY16F020011"],"award-info":[{"award-number":["LY16F020011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["91538111"],"award-info":[{"award-number":["91538111"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61620106009"],"award-info":[{"award-number":["61620106009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61429201"],"award-info":[{"award-number":["61429201"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ARO","award":["W911NF-15-1-0290"],"award-info":[{"award-number":["W911NF-15-1-0290"]}]},{"name":"Faculty Research Gift Awards by NEC Laboratories of America and Blippar"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/tcsvt.2017.2719043","type":"journal-article","created":{"date-parts":[[2017,6,23]],"date-time":"2017-06-23T18:51:24Z","timestamp":1498243884000},"page":"3030-3043","source":"Crossref","is-referenced-by-count":278,"title":["Learning Affective Features With a Hybrid Deep Model for Audio\u2013Visual Emotion Recognition"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8184-5088","authenticated-orcid":false,"given":"Shiqing","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9053-9314","authenticated-orcid":false,"given":"Shiliang","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4234-6099","authenticated-orcid":false,"given":"Tiejun","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Wen","family":"Gao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5165-4325","authenticated-orcid":false,"given":"Qi","family":"Tian","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-85729-932-1_19"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472109"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298854"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0788-3"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2016.7527309"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472191"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372886"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2010.09.020"},{"key":"ref60","doi-asserted-by":"crossref","first-page":"2794","DOI":"10.21437\/Interspeech.2010-739","article-title":"The INTERSPEECH 2010 paralinguistic challenge","author":"schuller","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/34.667881"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912051"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2014.11.014"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2671188.2749400"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_42"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2482228"},{"key":"ref65","first-page":"2285","article-title":"Compressing neural networks with the hashing trick","author":"chen","year":"2015","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref66","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1145\/2818346.2829994","article-title":"Video and image based emotion recognition challenges in the wild: Emotiw 2015","author":"dhall","year":"2015","journal-title":"Proc ACM Int Conf Multimodal Interact (ICMI)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.01.007"},{"key":"ref67","first-page":"3","article-title":"AVEC 2013&#x2014;The continuous audio\/visual emotion and depression recognition challenge","author":"valstar","year":"2013","journal-title":"Proc 21st ACM Int Conf Multimedia (MM)"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.09.117"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2661806.2661810"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2444731"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760128018"},{"key":"ref23","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638346"},{"key":"ref25","first-page":"2447","article-title":"A better way to pretrain deep Boltzmann machines","author":"hinton","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2009.5349454"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICDEW.2006.145"},{"key":"ref58","first-page":"868","article-title":"MARS: A video benchmark for large-scale person re-identification","author":"zheng","year":"2016","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000013087.49260.fb"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1186\/1687-6180-2012-20"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2008.08.005"},{"key":"ref54","author":"huang","year":"2001","journal-title":"Spoken Language Processing A Guide to Theory Algorithm and System Development"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2012.03.001"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638345"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.40"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-015-3180-6"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1080\/02564602.2015.1117403"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2553038"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-016-0823-x"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-012-1228-3"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2006.1621452"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2189550"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.52"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1142\/S1793351X13400023"},{"key":"ref19","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.921737"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.927665"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24571-8_47"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-009-0344-2"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2171334"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.37"},{"key":"ref49","first-page":"2225","article-title":"Using neutral speech models for emotional speech analysis","author":"busso","year":"2007","journal-title":"Proc INTERSPEECH"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.12"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.07.041"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/1027933.1027968"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/1322192.1322201"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1110"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/AFGR.1998.670990"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997637"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2011.5771366"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/8506638\/07956190.pdf?arnumber=7956190","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,30]],"date-time":"2022-07-30T00:35:19Z","timestamp":1659141319000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7956190\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":68,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2017.2719043","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,10]]}}}