{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T16:25:56Z","timestamp":1780676756919,"version":"3.54.1"},"reference-count":197,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100015539","name":"Australian Government","doi-asserted-by":"publisher","award":["10.13039\/100015539"],"award-info":[{"award-number":["10.13039\/100015539"]}],"id":[{"id":"10.13039\/100015539","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2021,4,1]]},"DOI":"10.1109\/taffc.2018.2890471","type":"journal-article","created":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T20:02:24Z","timestamp":1546372944000},"page":"524-543","source":"Crossref","is-referenced-by-count":166,"title":["Deep Learning for Human Affect Recognition: Insights and New Developments"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2282-8178","authenticated-orcid":false,"given":"Philipp V.","family":"Rouast","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6036-4282","authenticated-orcid":false,"given":"Marc T. P.","family":"Adam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8285-1903","authenticated-orcid":false,"given":"Raymond","family":"Chiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2015.07.005"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2013.2247823"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2016.12.005"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.02.003"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1145\/2070481.2070487"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/AFGR.1998.670949"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46672-9_58"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2829994"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.15"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2016.7813351"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2724555"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/VAST.2017.8585721"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref33","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Mach Learn Res"},{"key":"ref32","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","author":"sutskever","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref31","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"2011","journal-title":"Proc Int Conf Artif Intell Stat"},{"key":"ref30","first-page":"1033","article-title":"Learning recurrent neural networks with hessian-free optimization","author":"martens","year":"2011","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/35.41400"},{"key":"ref36","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc 25th Int Conf Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.1962.sp006837"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.97"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSP.2014.7015071"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553805"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1145\/2512530.2512532"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.25"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.600"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.20"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1145\/2663204.2666274"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1145\/2661806.2661813"},{"key":"ref187","first-page":"220","article-title":"Detecting autism, emotions and social signals using adaboost","author":"gosztolya","year":"2013","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref186","first-page":"543","article-title":"Combining modality specific deep neural networks for emotion recognition in video","author":"kahou","year":"2013","journal-title":"Proc Int Conf Multimodal Interact"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/ICDEW.2006.145"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","first-page":"1","article-title":"Scaling learning algorithms towards AI","author":"bengio","year":"2007","journal-title":"Large-Scale Kernel Machines"},{"key":"ref22","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref21","article-title":"The curse of dimensionality for local kernel machines","author":"bengio","year":"2005"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1561\/2200000006"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1515\/semi.1969.1.1.49"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-558701-3.50007-7"},{"key":"ref154","first-page":"33","article-title":"Body motion analysis for emotion recognition in serious games","author":"kaza","year":"2016","journal-title":"Proc Int Conf Universal Access in Hum -Comput Interact"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1561\/2000000004"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.9"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997630"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2014.7041743"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2788081"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49685-6_3"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993173"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477679"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/2682899"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1037\/h0077714"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2740923"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2763942"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM.2016.7822545"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2012.06.016"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1037\/10538-000"},{"key":"ref40","first-page":"38","article-title":"A critical review of recurrent neural networks for sequence learning","author":"lipton","year":"2015","journal-title":"arXiv 1506 00019"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2014.6890166"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/627892"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref164","first-page":"1517","article-title":"A database of german emotional speech","author":"burkhardt","year":"2005","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820699"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2635124"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947651"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1007\/s12193-015-0195-2"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S1071-5819(03)00051-X"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2007.79"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S1071-5819(03)00020-X"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.6"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/34.954607"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638346"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2003.817122"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.97.3.315"},{"key":"ref157","first-page":"312","article-title":"The INTERSPEECH 2009 emotion challenge","author":"schuller","year":"2009","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2010.1"},{"key":"ref158","first-page":"254","article-title":"The INTERSPEECH 2012 speaker trait challenge","author":"schuller","year":"2012","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref46","first-page":"153","article-title":"Greedy layer-wise training of deep networks","author":"bengio","year":"2007","journal-title":"Proc 19th Int Conf Neural Inf Process Syst"},{"key":"ref45","first-page":"693","article-title":"Efficient learning of deep Boltzmann machines","author":"salakhutdinov","year":"2010","journal-title":"Proc Int Conf Artif Intell Stat"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2016.03.011"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101299"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1486"},{"key":"ref41","first-page":"1724","article-title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation","author":"cho","year":"2017","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref44","first-page":"194","article-title":"Information processing in dynamical systems: Foundations of harmony theory","author":"smolensky","year":"1986","journal-title":"Parallel Distributed Processing volume 1 Foundations"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90014-2"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2515606"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2366127"},{"key":"ref71","first-page":"53","article-title":"Communication without words","volume":"2","author":"mehrabian","year":"1968","journal-title":"Psychology Today"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/79.911197"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/IIH-MSP.2014.59"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/SMARTCOMP.2014.7043872"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2830587"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997639"},{"key":"ref78","first-page":"813","article-title":"Multimodal emotion recognition using deep networks","author":"fadil","year":"2014","journal-title":"Proc Latin Amer Congress Biomed Eng"},{"key":"ref79","first-page":"1","article-title":"Understanding deep learning requires rethinking generalization","author":"zhang","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2713355"},{"key":"ref61","first-page":"808","article-title":"Disentangling factors of variation for facial expression recognition","author":"rifai","year":"2012","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952552"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2695999"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2014.11.007"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7351656"},{"key":"ref67","first-page":"255","article-title":"Music emotion recognition: A state of the art review","author":"kim","year":"2010","journal-title":"Proc Int Soc Music Inf Retrieval"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2011.6082328"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8640.2012.00456.x"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref195","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref196","first-page":"1","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc 31st Conf Neural Inf Process Syst"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3143009"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.07.026"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2830585"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2017.68"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3143008"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2713408"},{"key":"ref192","first-page":"23","article-title":"Regularization for deep learning: A taxonomy","author":"kuka?ka","year":"2017","journal-title":"ArXiv 1710 10686"},{"key":"ref91","first-page":"16","article-title":"A deep learning perspective on the origin of facial expressions","author":"breuer","year":"2017","journal-title":"arXiv 1705 01842"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532431"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1117\/1.JEI.25.6.061407"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2017.01.012"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997634"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997637"},{"key":"ref82","first-page":"1","article-title":"Deep learning using linear support vector machines","author":"tang","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2015.09.009"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref80","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997629"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2719043"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3143004"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.12"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.341"},{"key":"ref101","article-title":"The Toronto face dataset","author":"susskind","year":"2010"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912006"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/PlatCon.2017.7883728"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654984"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2013.58"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2012.03.001"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.02.013"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/ICSPCS.2015.7391796"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947700"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953131"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2015.7344669"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46687-3_1"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1637"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953106"},{"key":"ref138","first-page":"1","article-title":"SoundNet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2013.90"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3143006"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2672753"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2014.6889814"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952655"},{"key":"ref143","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/j.intcom.2008.10.011","article-title":"Fundamentals of physiological computing","volume":"21","author":"fairclough","year":"2008","journal-title":"Interact Comput"},{"key":"ref2","article-title":"Affective computing","author":"picard","year":"1995"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1016\/j.biopsycho.2010.01.017"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/1140.001.0001","author":"picard","year":"1997","journal-title":"Affective Computing"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/IWCIA.2016.7805744"},{"key":"ref109","first-page":"806","article-title":"CNN features off-the-shelf: An astounding baseline for recognition","author":"razavian","year":"2014","journal-title":"Proc IEEE Conf Comp Vis Pattern Recognit"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764438"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2830593"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2830596"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2662199"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299058"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.005"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130508"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2010.5543262"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2006.10.019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.52"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997638"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988258"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997632"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997636"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2830590"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-012-9368-5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133949"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2010.09.020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988264"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811641"},{"key":"ref119","first-page":"1096","article-title":"Unsupervised feature learning for audio classification using convolutional deep belief networks","author":"lee","year":"2009","journal-title":"Proc 22nd Int Conf Neural Inf Process Syst"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-3005-5_56"},{"key":"ref113","first-page":"1","article-title":"Deep neural networks with relativity learning for facial expression recognition","author":"guo","year":"2016","journal-title":"Proc Int Conf Multimedia Expo Workshops"},{"key":"ref116","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2017.23"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2009.5349350"},{"key":"ref123","first-page":"148","article-title":"The INTERSPEECH 2013 computational paralinguistics challenge","author":"schuller","year":"2013","journal-title":"Proc Annu Conf Int Speech Commun Assoc"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5165369\/9443045\/08598999.pdf?arnumber=8598999","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,13]],"date-time":"2024-07-13T19:06:58Z","timestamp":1720897618000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8598999\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,1]]},"references-count":197,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2018.2890471","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,1]]}}}