{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:47:13Z","timestamp":1776444433524,"version":"3.51.2"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053762","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"3507-3511","source":"Crossref","is-referenced-by-count":138,"title":["Multimodal Transformer Fusion for Continuous Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Jian","family":"Huang","sequence":"first","affiliation":[]},{"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[]},{"given":"Bin","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Zheng","family":"Lian","sequence":"additional","affiliation":[]},{"given":"Mingyue","family":"Niu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Audio visual emotion recognition with temporal alignment and perception attention","author":"chao","year":"2016"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3247"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967286"},{"key":"ref13","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref15","first-page":"35","article-title":"Phoneme recognition using time-delay neural networks","author":"waibel","year":"1995","journal-title":"Backpropagation Theory Architectures and Applications"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133953"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3266302.3266304"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2663204.2666274"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2014.11"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-3380-8"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133946"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.77"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638346"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1027933.1027968"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.4018\/jse.2010101605"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2663204.2666277"},{"key":"ref20","first-page":"255","article-title":"A concordance correlation coefficient to evaluate reproducibility","author":"lawrence","year":"1989","journal-title":"Biometrics"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988258"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053762.pdf?arnumber=9053762","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:25:48Z","timestamp":1656375948000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053762\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053762","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}