{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T22:59:29Z","timestamp":1783983569879,"version":"3.55.0"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Reserach Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003151","name":"Fonds de recherche du Qu\u00e9bec\u2014Nature et Technologies","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003151","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Biom. Behav. Identity Sci."],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1109\/tbiom.2022.3233083","type":"journal-article","created":{"date-parts":[[2023,1,4]],"date-time":"2023-01-04T18:32:59Z","timestamp":1672857179000},"page":"360-373","source":"Crossref","is-referenced-by-count":55,"title":["Audio\u2013Visual Fusion for Emotion Recognition in the Valence\u2013Arousal Space Using Joint Cross-Attention"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4698-9198","authenticated-orcid":false,"given":"R. Gnana","family":"Praveen","sequence":"first","affiliation":[{"name":"Department of Systems Engineering, Laboratoire d’imagerie, de vision et d’intelligence artificielle, École de technologie supérieure, Montreal, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Patrick","family":"Cardinal","sequence":"additional","affiliation":[{"name":"Department of Systems Engineering, Laboratoire d’imagerie, de vision et d’intelligence artificielle, École de technologie supérieure, Montreal, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6116-7945","authenticated-orcid":false,"given":"Eric","family":"Granger","sequence":"additional","affiliation":[{"name":"Department of Systems Engineering, Laboratoire d’imagerie, de vision et d’intelligence artificielle, École de technologie supérieure, Montreal, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2014.11"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01158-4"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553805"},{"key":"ref15","first-page":"1","article-title":"Cross attentional audio-visual fusion for dimensional emotion recognition","author":"rajasekhar","year":"2021","journal-title":"Proc FG"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988258"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00397"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811642"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240578"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3428690.3429153"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683477"},{"key":"ref55","first-page":"14200","article-title":"Attention bottlenecks for multimodal fusion","author":"nagrani","year":"2021","journal-title":"Proc NIPS"},{"key":"ref10","article-title":"Cross-attentional audio-visual fusion for weakly-supervised action Localization","author":"lee","year":"2021","journal-title":"Proc ICLR"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764438"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.03.007"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.10.011"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00402"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-200"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2228"},{"key":"ref46","article-title":"The kinetics human action video dataset","author":"kay","year":"2017","journal-title":"arXiv 1705 06950"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104167"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00139"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref42","first-page":"4005","article-title":"Cross attention network for few-shot classification","author":"hou","year":"2019","journal-title":"Proc NIPS"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912064"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2012.03.001"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2695999"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4939-1456-2_7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1999.786997"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2057231"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00406"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-012-9368-5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992972"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.9"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1037\/h0054570"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683898"},{"key":"ref35","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00098"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3417960"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00729"},{"key":"ref30","first-page":"4243","article-title":"Multimodal emotion recognition using cross-modal attention and 1D convolutional neural networks","author":"krishna","year":"2020","journal-title":"Proc INTERSPEECH"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5364"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1080\/02699939208411068"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-08491-6_5"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1832"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3024218"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3063612"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00266"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2019.8914655"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00261"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00056"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00396"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00109"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811641"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00408"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383573"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00126"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3264869.3264873"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2016.11.020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2312"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811640"},{"key":"ref61","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume":"9","author":"glorot","year":"2010","journal-title":"Proc ICAIS"}],"container-title":["IEEE Transactions on Biometrics, Behavior, and Identity Science"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8423754\/10210132\/10005783.pdf?arnumber=10005783","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T18:13:52Z","timestamp":1693246432000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10005783\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7]]},"references-count":68,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tbiom.2022.3233083","relation":{},"ISSN":["2637-6407"],"issn-type":[{"value":"2637-6407","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7]]}}}