{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T21:29:07Z","timestamp":1772227747355,"version":"3.50.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100017700","name":"Henan Provincial Science and Technology Research Project","doi-asserted-by":"publisher","award":["242102210101"],"award-info":[{"award-number":["242102210101"]}],"id":[{"id":"10.13039\/501100017700","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017700","name":"Henan Provincial Science and Technology Research Project","doi-asserted-by":"publisher","award":["252102210214"],"award-info":[{"award-number":["252102210214"]}],"id":[{"id":"10.13039\/501100017700","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Henan Provincial Key Scientific Research Projects Program for Higher Education Institutions","award":["25A520053"],"award-info":[{"award-number":["25A520053"]}]},{"name":"Henan Province Intelligent Transportation Video Image Perception and Recognition Engineering Technology Research Center under Grant Yukeshi [2024] No. 1"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3663574","type":"journal-article","created":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:56:35Z","timestamp":1770843395000},"page":"28229-28244","source":"Crossref","is-referenced-by-count":0,"title":["SADGR: Adaptive Cross-Modal Emotion Recognition via Self-Supervised Alignment and Dynamic Gating"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6800-3873","authenticated-orcid":false,"given":"Junjun","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Software, Henan University of Engineering, Zhengzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0065-3419","authenticated-orcid":false,"given":"Jianjing","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Software, Zhengzhou University of Industrial Technology, Zhengzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3072-5227","authenticated-orcid":false,"given":"Yanyang","family":"Hou","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Zhengzhou University of Industrial Technology, Zhengzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2630-3723","authenticated-orcid":false,"given":"Giseop","family":"Noh","sequence":"additional","affiliation":[{"name":"Department of Software and Communications Engineering, Hongik University, Sejong-si, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3299-7449","authenticated-orcid":false,"given":"Fengxi","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Software, Henan University of Engineering, Zhengzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108837"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2020.3038167"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/e24111691"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.02.003"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p18-1209"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109259"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112220"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref16","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3031549"},{"key":"ref18","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref19","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref20","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","author":"Shi","year":"2022","journal-title":"arXiv:2201.02184"},{"key":"ref21","article-title":"UniVL: A unified video and language pre-training model for multimodal understanding and generation","author":"Luo","year":"2020","journal-title":"arXiv:2002.06353"},{"key":"ref22","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","author":"Su","year":"2019","journal-title":"arXiv:1908.08530"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9747669"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9747631"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403305"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00503"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01973"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref31","article-title":"An image is worth 16$\\times$\n16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413690"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6431"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.111346"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3429301"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2024.3378570"},{"key":"ref42","article-title":"Recent advances in multimodal affective computing: A review","author":"Liang","year":"2024","journal-title":"arXiv:2409.07388"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11393599.pdf?arnumber=11393599","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T20:50:54Z","timestamp":1772225454000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11393599\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3663574","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}