{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T16:38:19Z","timestamp":1776184699109,"version":"3.50.1"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"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":["IEEE Trans. Consumer Electron."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/tce.2025.3532322","type":"journal-article","created":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T18:25:58Z","timestamp":1737483958000},"page":"1092-1101","source":"Crossref","is-referenced-by-count":26,"title":["Joint Multi-Scale Multimodal Transformer for Emotion Using Consumer Devices"],"prefix":"10.1109","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8020-3590","authenticated-orcid":false,"given":"Mustaqeem","family":"Khan","sequence":"first","affiliation":[{"name":"College of Information Technology, United Arab Emirates University, Al Ain, UAE"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8407-5971","authenticated-orcid":false,"given":"Jamil","family":"Ahmad","sequence":"additional","affiliation":[{"name":"College of Information Technology, United Arab Emirates University, Al Ain, UAE"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6490-4648","authenticated-orcid":false,"given":"Wail","family":"Gueaieb","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON, Canada"}]},{"given":"Giulia","family":"De Masi","sequence":"additional","affiliation":[{"name":"Technology Innovation Institute, Abu Dhabi, UAE"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4217-1372","authenticated-orcid":false,"given":"Fakhri","family":"Karray","sequence":"additional","affiliation":[{"name":"Computer Vision, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7690-8547","authenticated-orcid":false,"given":"Abdulmotaleb","family":"El Saddik","sequence":"additional","affiliation":[{"name":"Computer Vision, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3094362"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104167"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2022.104569"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101299"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2023.3236972"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2023.3325317"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tce.2024.3438841"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1080\/02699939208411068"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3165180"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3357543"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2019.8914655"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00607"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tce.2024.3435881"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2023.3263672"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00278"},{"key":"ref16","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. 33RD Conf. Neural Inf. Process. Syst.","volume":"32","author":"Lu"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2023.3319111"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764438"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00056"},{"key":"ref20","article-title":"Distribution matching for heterogeneous multi-task learning: A large-scale face study","author":"Kollias","year":"2021","journal-title":"arXiv:2105.03790"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.03.007"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00396"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00641"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747278"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.107567"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106981"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053762"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3195739"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3259010"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2024.3461148"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3357480"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/FG52635.2021.9667055"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3390841"},{"key":"ref35","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref36","article-title":"Resnet in resnet: Generalizing residual architectures","author":"Targ","year":"2016","journal-title":"arXiv:1603.08029"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095234"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2012.03.001"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00611"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993165"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref42","article-title":"MELD: A multimodal multi-party dataset for emotion recognition in conversations","author":"Poria","year":"2018","journal-title":"arXiv:1810.02508"},{"key":"ref43","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1015"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.224"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.367"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.547"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.123"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746464"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-14600-0"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122946"},{"issue":"11","key":"ref53","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref54","first-page":"873","article-title":"Context-dependent sentiment analysis in user-generated videos","volume-title":"Proc. 55th Annu. Meeting Assoc. Comput. Linguist.","author":"Poria"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/752"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3390\/s21144913"},{"key":"ref58","article-title":"DialogueTRM: Exploring the intra-and inter-modal emotional behaviors in the conversation","author":"Mao","year":"2020","journal-title":"arXiv:2010.07637"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3390\/s23115184"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126427"}],"container-title":["IEEE Transactions on Consumer Electronics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/30\/11038962\/10848157.pdf?arnumber=10848157","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T05:20:40Z","timestamp":1750224040000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10848157\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":60,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tce.2025.3532322","relation":{},"ISSN":["0098-3063","1558-4127"],"issn-type":[{"value":"0098-3063","type":"print"},{"value":"1558-4127","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}