{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:09:57Z","timestamp":1783436997355,"version":"3.54.6"},"reference-count":78,"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":"Strategic Priority Research Program of Chinese Academy of Sciences","award":["XDC08050200"],"award-info":[{"award-number":["XDC08050200"]}]},{"name":"Ximalaya Inc."}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3096037","type":"journal-article","created":{"date-parts":[[2021,8,17]],"date-time":"2021-08-17T20:36:05Z","timestamp":1629232565000},"page":"2617-2629","source":"Crossref","is-referenced-by-count":78,"title":["Information Fusion in Attention Networks Using Adaptive and Multi-Level Factorized Bilinear Pooling for Audio-Visual Emotion Recognition"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7878-6531","authenticated-orcid":false,"given":"Hengshun","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2387-0389","authenticated-orcid":false,"given":"Jun","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanyuan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3843-3920","authenticated-orcid":false,"given":"Qing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing-Feng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1892-2551","authenticated-orcid":false,"given":"Chin-Hui","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2928625"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1199"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2012.03.001"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638345"},{"key":"ref76","first-page":"2579","article-title":"Visualizing data using T-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3264992"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682896"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1520"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115546"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2561"},{"key":"ref78","doi-asserted-by":"crossref","DOI":"10.1088\/1742-6596\/1873\/1\/012092","article-title":"Emotion recognition model based on multimodal decision fusion","volume":"1873","author":"zheng","year":"2021","journal-title":"J Phys Conf Ser"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2018.08.035"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1049\/iet-spr.2013.0446"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2014.10.011"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3355720"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3247"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683725"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1432"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1353"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952655"},{"key":"ref62","first-page":"1","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2014","journal-title":"Proc 28th Int Conf Neural Inf Process Syst Workshop Conf"},{"key":"ref61","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"2011","journal-title":"Proc 14th Int Conf Artif Intell Statist Workshop Conf Proc"},{"key":"ref63","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"king","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3143009"},{"key":"ref64","article-title":"Fer-2013 face database","author":"carrier","year":"2013"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-018-0960-9"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.41"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3264989"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.229"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref69","first-page":"1","article-title":"Hadamard product for low-rank bilinear pooling","author":"kim","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/S135561770606111X"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.visinf.2019.10.003"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1180639.1180661"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3355719"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997632"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2719043"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3355713"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8851942"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2044"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-009-0344-2"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2189550"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952552"},{"key":"ref58","first-page":"2453","article-title":"Multimodal emotion recognition using facial expressions, body gestures, speech, and text modalities","volume":"8","author":"mahesh","year":"2019","journal-title":"Int J Eng Adv Technol"},{"key":"ref57","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2012.26"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICDEW.2006.145"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2009.2030637"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.921737"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/34.908962"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3252"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2860246"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659587"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACIIAsia.2018.8470342"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1242"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803603"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3264978"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.10.005"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5772\/54002"},{"key":"ref19","first-page":"1020","article-title":"Audio-Visual based emotion recognition-a new approach","volume":"2","author":"song","year":"2004","journal-title":"Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5565\/rev\/elcvia.795"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2014.07.005"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3264993"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-200"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2006.09.007"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3353739"},{"key":"ref7","first-page":"546","article-title":"Emotiw 2019: Automatic emotion, engagement and cohesion prediction tasks","author":"a","year":"2019","journal-title":"Proc Int Conf Multimodal Interact"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2017.03.016"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451359"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451764"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8802941"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3353753"},{"key":"ref42","article-title":"Facial action coding system (FACs","author":"ekman","year":"2002"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2093"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00109"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09484766.pdf?arnumber=9484766","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:58Z","timestamp":1652194438000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9484766\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3096037","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}