{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T20:55:14Z","timestamp":1775508914645,"version":"3.50.1"},"reference-count":78,"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":["U22A2096"],"award-info":[{"award-number":["U22A2096"]}],"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":["62036007"],"award-info":[{"award-number":["62036007"]}],"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":["62376235"],"award-info":[{"award-number":["62376235"]}],"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":["62306178"],"award-info":[{"award-number":["62306178"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Scientific and Technological Innovation Teams in Shaanxi Province","award":["2025RS-CXTD-011"],"award-info":[{"award-number":["2025RS-CXTD-011"]}]},{"name":"Shaanxi Province Core Technology Research and Development Project","award":["2024QY2-GJHX-11"],"award-info":[{"award-number":["2024QY2-GJHX-11"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["QTZX23042"],"award-info":[{"award-number":["QTZX23042"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"GDST Basic Research Fund","award":["2022A1515011652"],"award-info":[{"award-number":["2022A1515011652"]}]},{"name":"GDST Basic Research Fund","award":["2024A1515012399"],"award-info":[{"award-number":["2024A1515012399"]}]},{"name":"HKBU Faculty Niche Research","award":["RC-FNRA-IG\/22-23\/SCI\/04"],"award-info":[{"award-number":["RC-FNRA-IG\/22-23\/SCI\/04"]}]},{"name":"HKBU CSD Departmental Incentive Scheme"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3604916","type":"journal-article","created":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T19:31:31Z","timestamp":1756755091000},"page":"7864-7875","source":"Crossref","is-referenced-by-count":3,"title":["Knowledge-Enhanced Facial Expression Recognition With Emotional-to-Neutral Transformation"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7153-6676","authenticated-orcid":false,"given":"Hangyu","family":"Li","sequence":"first","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks, School of Telecommunications Engineering, Xidian University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5884-2347","authenticated-orcid":false,"given":"Yihan","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks, School of Telecommunications Engineering, Xidian University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6115-5194","authenticated-orcid":false,"given":"Jiangchao","family":"Yao","sequence":"additional","affiliation":[{"name":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4695-6134","authenticated-orcid":false,"given":"Nannan","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks, School of Telecommunications Engineering, Xidian University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7985-0037","authenticated-orcid":false,"given":"Xinbo","family":"Gao","sequence":"additional","affiliation":[{"name":"Chongqing Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications, Chongqing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6338-0958","authenticated-orcid":false,"given":"Bo","family":"Han","sequence":"additional","affiliation":[{"name":"TMLR Group, Department of Computer Science, Hong Kong Baptist University, Hong Kong SAR, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2060716"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1055-1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2981446"},{"issue":"11","key":"ref4","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref5","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.277"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_6"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_24"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00358"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01857"},{"key":"ref13","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","year":"2021"},{"key":"ref14","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00030"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1037\/h0077714"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0059-7"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2829994"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141604"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_14"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413620"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3049955"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00618"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_38"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25477"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2956143"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3093397"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3347849"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109368"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01965"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3186536"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16465"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01471"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01892"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.1.6166.771"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3355637"},{"key":"ref38","first-page":"1","article-title":"Visual classification via description from large language models","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Menon","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01934"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687508"},{"key":"ref41","first-page":"1","article-title":"Prompting visual-language models for dynamic facial expression recognition","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Zhao","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/FG59268.2024.10581982"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681583"},{"key":"ref44","article-title":"A $^{3}$ lign-dfer: Pioneering comprehensive dynamic affective alignment for dynamic facial expression recognition with clip","author":"Tao","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3424777"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_14"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01556-7"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00231"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3197761"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3263886"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00757"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00669"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_11"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3397701"},{"key":"ref55","first-page":"1","article-title":"Using language to extend to unseen domains","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Dunlap","year":"2023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2740923"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00693"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993165"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2010.5543262"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref61","article-title":"Clip surgery for better explainability with enhancement in open-vocabulary tasks","author":"Li","year":"2023"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref63","first-page":"17616","article-title":"Relative uncertainty learning for facial expression recognition","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","volume":"34","author":"Zhang","year":"2021"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00245"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00148"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3301209"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3122146"},{"key":"ref68","article-title":"Mvt: Mask vision transformer for facial expression recognition in the wild","author":"Li","year":"2021"},{"key":"ref69","article-title":"Au-aware vision transformers for biased facial expression recognition","author":"Mao","year":"2022"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3226473"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521788"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2886767"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3131222"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00413"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3031602"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3285231"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00339"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11146491.pdf?arnumber=11146491","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:57:17Z","timestamp":1775505437000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11146491\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3604916","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}