{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:23:47Z","timestamp":1777890227381,"version":"3.51.4"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01169","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12581-12591","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal Prompt Alignment for Facial Expression Recognition"],"prefix":"10.1109","author":[{"given":"Fuyan","family":"Ma","sequence":"first","affiliation":[{"name":"Chinese Academy of Military Science"}]},{"given":"Yiran","family":"He","sequence":"additional","affiliation":[{"name":"Changchun University of Science and Technology"}]},{"given":"Bin","family":"Sun","sequence":"additional","affiliation":[{"name":"Hunan University"}]},{"given":"Shutao","family":"Li","sequence":"additional","affiliation":[{"name":"Hunan University"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993165"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72390-2_72"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3141400"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02225"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref9","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International Conference on Machine Learning","volume":"2","author":"Jia"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref13","first-page":"8","article-title":"Mvit: Mask vision transformer for facial expression recognition in the wild","author":"Li","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3049955"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687508"},{"issue":"3","key":"ref16","first-page":"8","article-title":"Knowledge-enhanced facial expression recognition with emotional-to-neutral transformation","volume":"2","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2868382"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2981446"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2886767"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521788"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73001-6_17"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw.2010.5543262"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2021.3122146"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3285231"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3335"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2740923"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02544"},{"key":"ref28","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","volume":"2","author":"Radford"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2005.1530069"},{"key":"ref30","first-page":"2","article-title":"Vl-bert: Pre-training of generic visuallinguistic representations","author":"Su","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2216"},{"key":"ref32","first-page":"65","article-title":"Induced disgust, happiness and surprise: an addition to the mmi facial expression database","volume-title":"Proceedings of International Workshop on EMOTION: Corpora for Research on Emotion and Affect","volume":"1","author":"Valstar"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1080\/02699930701782153"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00693"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2956143"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3267774"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02206"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-78157-8_11"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00358"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2022.3226473"},{"key":"ref41","first-page":"6757","article-title":"Visuallanguage prompt tuning with knowledge-guided context optimization","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","volume":"3","author":"Yao"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_14"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3072786"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01897"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2011.07.002"},{"key":"ref46","first-page":"2","article-title":"Prompting visuallanguage models for dynamic facial expression recognition","author":"Zhao","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3093397"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00339"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3424777"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11449042.pdf?arnumber=11449042","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:33:44Z","timestamp":1777613624000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11449042\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01169","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}