{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:15:04Z","timestamp":1778051704021,"version":"3.51.4"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00265","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"2700-2709","source":"Crossref","is-referenced-by-count":0,"title":["Divide and Refine: Enhancing Multimodal Representation and Explainability for Emotion Recognition in Conversation"],"prefix":"10.1109","author":[{"given":"Anh-Tuan","family":"Mai","sequence":"first","affiliation":[{"name":"VNU University of Engineering and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cam-Van Thi","family":"Nguyen","sequence":"additional","affiliation":[{"name":"VNU University of Engineering and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Duc-Trong","family":"Le","sequence":"additional","affiliation":[{"name":"VNU University of Engineering and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.iswa.2022.200171"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/e16042161"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref6","article-title":"What to align in multimodal contrastive learning?","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Dufumier"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1015"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.224"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1193"},{"key":"ref11","article-title":"Deberta: Decoding-enhanced bert with disentangled attention","author":"He","year":"2006"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.547"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747397"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.440"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/e19070318"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.306"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3581236"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3141237"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1192"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1430"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3656580"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3271019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1046"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.937"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.63317\/3eikm2yttbsc"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126866"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17625"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00596"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/en14113086"},{"key":"ref33","article-title":"Nonnegative decomposition of multivariate information","author":"Williams","year":"2010"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3678957.3685716"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3093397"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492054.pdf?arnumber=11492054","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:24:43Z","timestamp":1778048683000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492054\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00265","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}