{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:25:37Z","timestamp":1780637137521,"version":"3.54.1"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095234","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":19,"title":["Recursive Joint Attention for Audio-Visual Fusion in Regression Based Emotion Recognition"],"prefix":"10.1109","author":[{"given":"R Gnana","family":"Praveen","sequence":"first","affiliation":[{"name":"École de Technologie supérieure,Laboratoire d’Imagerie, de Vision et d’Intelligence Artificielle (LIVIA),Montreal,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric","family":"Granger","sequence":"additional","affiliation":[{"name":"École de Technologie supérieure,Laboratoire d’Imagerie, de Vision et d’Intelligence Artificielle (LIVIA),Montreal,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Patrick","family":"Cardinal","sequence":"additional","affiliation":[{"name":"École de Technologie supérieure,Laboratoire d’Imagerie, de Vision et d’Intelligence Artificielle (LIVIA),Montreal,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00261"},{"key":"ref12","article-title":"Multimodal sequence fusion via recursive attention for emotion recognition","author":"beard","year":"2018","journal-title":"CoNLL"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240578"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3428690.3429153"},{"key":"ref20","article-title":"Analysing affective behavior in the first abaw competition","author":"kollias","year":"2020","journal-title":"FG 2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00397"},{"key":"ref11","article-title":"Learning salient features for multimodal emotion recognition with recurrent neural networks and attention based fusion","author":"darshana","year":"2019","journal-title":"Proc of AVSP"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00408"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967286"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00056"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.03.007"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref16","first-page":"445","article-title":"Videobased emotion recognition using cnn-rnn and c3d hybrid networks","author":"fan","year":"2016","journal-title":"ACM ICMI"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01158-4"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00406"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2022.3233083"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383573"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00278"},{"key":"ref4","article-title":"Cross attentional audio-visual fusion for dimensional emotion recognition","author":"rajasekhar","year":"2021","journal-title":"FG"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00266"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.10.011"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"1301","DOI":"10.1109\/JSTSP.2017.2764438","article-title":"End-to-end multimodal emotion recognition using deep neural networks","volume":"11","author":"tzirakis","year":"2017","journal-title":"IEEE J of Selected Topics in Signal Processing"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095234.pdf?arnumber=10095234","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:06:25Z","timestamp":1700507185000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095234\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095234","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}