{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T17:47:49Z","timestamp":1793987269164,"version":"4.8.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"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":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956592","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T19:34:13Z","timestamp":1669750453000},"page":"2822-2828","source":"Crossref","is-referenced-by-count":71,"title":["Self-attention fusion for audiovisual emotion recognition with incomplete data"],"prefix":"10.1109","author":[{"given":"Kateryna","family":"Chumachenko","sequence":"first","affiliation":[{"name":"Tampere University,Department of Computing Sciences,Tampere,Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexandros","family":"Iosifidis","sequence":"additional","affiliation":[{"name":"Aarhus University,Department of Electrical and Computer Engineering,Aarhus,Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Moncef","family":"Gabbouj","sequence":"additional","affiliation":[{"name":"Tampere University,Department of Computing Sciences,Tampere,Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Deep multimodal fusion by channel exchanging","volume":"33","author":"wang","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Audiovisual slowfast networks for video recognition","author":"xiao","year":"2020"},{"key":"ref12","article-title":"Multimodal end-to-end autonomous driving","author":"xiao","year":"2020","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"ref13","article-title":"Learning to ignore: rethinking attention in cnns","author":"laakom","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref15","first-page":"4243","article-title":"Multimodal emotion recognition using cross-modal attention and 1d convolutional neural networks","author":"krishna","year":"2020","journal-title":"InterSpeech"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053762"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/s18072074"},{"key":"ref18","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2750679"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2740923"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/s20030592"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2936124"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2017.08.003"},{"key":"ref8","first-page":"13 289","article-title":"Mmtm: Multimodal transfer module for cnn fusion","author":"joze","year":"2020","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16465"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2019.04.017"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2017.7510622"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107660"},{"key":"ref20","article-title":"Pytorch image models","author":"wightman","year":"2019"},{"key":"ref22","article-title":"Multi-task cascaded convolutional networks (mtcnn) for face detection and facial landmark alignment","volume":"13","author":"gradilla","year":"2020","journal-title":"link] Acessado em"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","location":"Montreal, QC, Canada","start":{"date-parts":[[2022,8,21]]},"end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09956592.pdf?arnumber=9956592","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T20:05:01Z","timestamp":1671480301000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956592\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956592","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}