{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T06:00:05Z","timestamp":1783231205474,"version":"3.54.6"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Shaanxi Provincial Key R&D Program","award":["2017KW-ZD-14"],"award-info":[{"award-number":["2017KW-ZD-14"]}]},{"DOI":"10.13039\/501100013314","name":"Higher Education Discipline Innovation Project","doi-asserted-by":"publisher","award":["B16039"],"award-info":[{"award-number":["B16039"]}],"id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011878","name":"Vlaamse regering","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011878","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tmm.2020.3037496","type":"journal-article","created":{"date-parts":[[2020,11,12]],"date-time":"2020-11-12T21:06:14Z","timestamp":1605215174000},"page":"4171-4183","source":"Crossref","is-referenced-by-count":127,"title":["Transformer Encoder With Multi-Modal Multi-Head Attention for Continuous Affect Recognition"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7164-5840","authenticated-orcid":false,"given":"Haifeng","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6238-8499","authenticated-orcid":false,"given":"Dongmei","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1774-2970","authenticated-orcid":false,"given":"Hichem","family":"Sahli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3243019"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053762"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref33","first-page":"73","article-title":"Multimodal affective dimension prediction using deep bidirectional long short-term memory recurrent neural networks","author":"lang","year":"2015","journal-title":"Proc Int Workshop Audio\/Vis Emotion Challenge"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-7313-1"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3266302.3266313"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682896"},{"key":"ref37","first-page":"237","article-title":"Gradient flow in recurrent nets: The difficulty of learning longterm dependencies","author":"kolen","year":"2001","journal-title":"Proc IEEE Field Guide Dynamical Recurrent Netw"},{"key":"ref36","article-title":"Attention is all you need","author":"vaswani","year":"2017"},{"key":"ref35","article-title":"Strength modelling for real-worldautomatic continuous affect recognition from audiovisual signals","volume":"65","author":"jing","year":"2017","journal-title":"Image Vis Comput"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2871949"},{"key":"ref60","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"bai","year":"2018"},{"key":"ref62","article-title":"Deep residual learning for image recognition","author":"he","year":"2015"},{"key":"ref61","article-title":"Meta-learning with temporal convolutions","author":"mishra","year":"2017"},{"key":"ref63","article-title":"Layer Normalization","author":"ba","year":"2016","journal-title":"arXiv 1607 06450"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952552"},{"key":"ref64","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2940224"},{"key":"ref65","article-title":"Deep residual learning for image recognition","author":"he","year":"2015"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683801"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3266302.3266304"},{"key":"ref68","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume":"9","author":"glorot","year":"2010","journal-title":"J Mach Learn Res - Proc Track"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2003.817122"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988264"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2012.03.001"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3347320.3357692"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133946"},{"key":"ref21","first-page":"47","article-title":"Speech-based continuous emotion prediction by learning perception responses related to salient events: A study based on vocal affect bursts and cross-cultural affect in avec 2018","author":"gamage","year":"2018","journal-title":"Proc Audio\/Vis Emotion Challenge Workshop"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764438"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133952"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-548"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3347320.3357690"},{"key":"ref50","author":"ekman","year":"0","journal-title":"What the Face Reveals Basic and Applied Studies of Spontaneous Expression using the Facial Action Coding System (FACS)"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.psych.54.101601.145102"},{"key":"ref59","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume":"abs 1810 4805","author":"devlin","year":"2018","journal-title":"CoRR"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1564"},{"key":"ref56","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.12021","article-title":"Memory fusion network for multi-view sequential learning","author":"zadeh","year":"2018"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811634"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811640"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.03.001"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2388676.2388758"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2512530.2512533"},{"key":"ref40","article-title":"Factorized multimodal transformer for multimodal sequential learning","volume":"abs 1911 9826","author":"zadeh","year":"2019","journal-title":"CoRR"},{"key":"ref12","year":"2014","journal-title":"Proceedings of the 4th International Workshop on Audio\/Visual Emotion Challenge - AVEC '14"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988258"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133953"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3266302.3266316"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3347320.3357688"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3266302.3266304"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3347320.3357691"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811642"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1180995.1181044"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.37"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.9"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.02.003"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.52"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133949"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1037\/h0077714"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2944808"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2010.2057200"},{"key":"ref47","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc 27th Int Conf Neural Inf Process Syst - Volume 2"},{"key":"ref42","first-page":"137","article-title":"Psychological models of emotion","author":"scherer","year":"2000","journal-title":"The Neuropsychology of Emotion"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1037\/h0077714"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553805"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.20"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9296985\/09257201.pdf?arnumber=9257201","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,27]],"date-time":"2022-11-27T22:15:22Z","timestamp":1669587322000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9257201\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/tmm.2020.3037496","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}