{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:04:16Z","timestamp":1772553856181,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747157","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7357-7361","source":"Crossref","is-referenced-by-count":34,"title":["AuxFormer: Robust Approach to Audiovisual Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Lucas","family":"Goncalves","sequence":"first","affiliation":[{"name":"The University of Texas at Dallas,Multimodal Signal Processing (MSP) Laboratory,Department of Electrical and Computer Engineering,Richardson,TX,USA,75080"}]},{"given":"Carlos","family":"Busso","sequence":"additional","affiliation":[{"name":"The University of Texas at Dallas,Multimodal Signal Processing (MSP) Laboratory,Department of Electrical and Computer Engineering,Richardson,TX,USA,75080"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.921737"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2663204.2666277"},{"key":"ref13","first-page":"27","article-title":"Learning the kernel matrix with semidefinite programming","volume":"5","author":"lanckriet","year":"2004","journal-title":"Journal of Machine Learning Research"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.07.041"},{"key":"ref15","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS 2017)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486455"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1207"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2515617"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3395035.3425202"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.857572"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2594"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2003.817150"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.03.006"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00021"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(02)00084-5"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2493525"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","article-title":"SSD: Single shot multibox detector","volume":"9905","author":"liu","year":"2016","journal-title":"European Conference on Computer Vision (ECCV 2016)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-56"},{"key":"ref23","first-page":"1459","article-title":"OpenSMILE: the Munich versatile and fast open-source audio feature extractor","author":"eyben","year":"2010","journal-title":"ACM International Conference on Multimedia (MM 2010)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2815268"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2975922"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747157.pdf?arnumber=9747157","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:05:46Z","timestamp":1660593946000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747157\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747157","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}