{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T18:25:26Z","timestamp":1780424726994,"version":"3.54.1"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62361166629"],"award-info":[{"award-number":["62361166629"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62225113"],"award-info":[{"award-number":["62225113"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2042025YXA006"],"award-info":[{"award-number":["2042025YXA006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Project of Science and Technology Innovation of Hubei Province","award":["2024BCA003"],"award-info":[{"award-number":["2024BCA003"]}]},{"name":"Innovative Research Group Project of Hubei Province","award":["2024AFA017"],"award-info":[{"award-number":["2024AFA017"]}]},{"name":"Key Project of the Health Commission of Hubei Province","award":["WJ2023Z003"],"award-info":[{"award-number":["WJ2023Z003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3608664","type":"journal-article","created":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T17:48:36Z","timestamp":1758217716000},"page":"6180-6191","source":"Crossref","is-referenced-by-count":1,"title":["Gradient and Structure Consistency in Multimodal Emotion Recognition"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9433-2281","authenticated-orcid":false,"given":"QingHongYa","family":"Shi","sequence":"first","affiliation":[{"name":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3989-7655","authenticated-orcid":false,"given":"Mang","family":"Ye","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4819-293X","authenticated-orcid":false,"given":"Wenke","family":"Huang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0059-8458","authenticated-orcid":false,"given":"Bo","family":"Du","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofen","family":"Zong","sequence":"additional","affiliation":[{"name":"Department of Psychiatry, Renmin Hospital of Wuhan University, Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3106813"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01335"},{"key":"ref3","article-title":"Catch your emotion: Sharpening emotion perception in multimodal large language models","volume-title":"Proc. 47nd Int. Conf. Mach. Learn.","author":"Fang"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2416634"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.compedu.2019.103649"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3247876"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3261743"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.01.157"},{"issue":"6","key":"ref9","first-page":"2275","article-title":"A review of public social behavior understanding and hidden groups discovery","volume":"30","author":"Li","year":"2025","journal-title":"J. Image Graph."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00641"},{"key":"ref12","article-title":"Learning factorized multimodal representations","volume-title":"Proc. Int. Conf. Represent. Learn.","author":"Tsai"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547754"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01918"},{"key":"ref16","first-page":"18347","article-title":"Fishr: Invariant gradient variances for out-of-distribution generalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rame"},{"key":"ref17","article-title":"Gradient matching for domain generalization","author":"Shi","year":"2021","journal-title":"arXiv:2104.09937"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096655"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2970494"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0055"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00258"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00804"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2017.8273573"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2070481.2070509"},{"key":"ref27","first-page":"973","article-title":"Utterance-level multimodal sentiment analysis","volume-title":"Proc. 51st Annu. Meeting Assoc. Comput. Linguistics","author":"P\u00e9rez-Rosas"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993176"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref30","article-title":"Select-additive learning: Improving generalization in multimodal sentiment analysis","author":"Wang","year":"2016","journal-title":"arXiv:1609.05244"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3274829"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i20.35416"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3222023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547755"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-demo.20"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3183830"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_27"},{"key":"ref42","article-title":"Coupled mamba: Enhanced multi-modal fusion with coupled state space model","author":"Li","year":"2024","journal-title":"arXiv:2405.18014"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32146"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02546"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2025.3553149"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3073857"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3277794"},{"key":"ref48","article-title":"EmoLLM: Multimodal emotional understanding meets large language models","author":"Yang","year":"2024","journal-title":"arXiv:2406.16442"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02300"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3290594"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13801-3"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-15937-4_65"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87199-4_16"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.343"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547906"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"ref58","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics. Hum. Lang. Technol.","author":"Devlin"},{"key":"ref59","first-page":"12449","article-title":"Wav2Vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Baevski"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477553"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016892"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.11.022"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.421"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-3309"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126373"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446922"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11165766.pdf?arnumber=11165766","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T05:24:43Z","timestamp":1759296283000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11165766\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3608664","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}