{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T21:01:18Z","timestamp":1775509278235,"version":"3.50.1"},"reference-count":91,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62171309"],"award-info":[{"award-number":["62171309"]}],"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":["62306061"],"award-info":[{"award-number":["62306061"]}],"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":["62576076"],"award-info":[{"award-number":["62576076"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"China Computer Federation (CCF)-Tencent Rhino-Bird Open Research Fund; and in part by the SongShan Lake HPC Center","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3675883","type":"journal-article","created":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T19:52:55Z","timestamp":1774554775000},"page":"3479-3494","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Granularity Facial Emotional Representation With Unlabeled Data and Textual Supervision"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2353-2436","authenticated-orcid":false,"given":"Kaishen","family":"Yuan","sequence":"first","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0422-6616","authenticated-orcid":false,"given":"Zitong","family":"Yu","sequence":"additional","affiliation":[{"name":"Great Bay University, Dongguan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2242-6139","authenticated-orcid":false,"given":"Xin","family":"Liu","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bohao","family":"Xing","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3706-6256","authenticated-orcid":false,"given":"Yuting","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8946-7472","authenticated-orcid":false,"given":"Weicheng","family":"Xie","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1420-0815","authenticated-orcid":false,"given":"Linlin","family":"Shen","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6478-8699","authenticated-orcid":false,"given":"Bj\u00f6rn W.","family":"Schuller","sequence":"additional","affiliation":[{"name":"Technical University of Munich, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2981446"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1037\/t27734-000"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00840"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2731763"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.277"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00669"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_14"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00245"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3049955"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16465"},{"key":"ref11","article-title":"MVT: Mask vision transformer for facial expression recognition in the wild","author":"Li","year":"2021","journal-title":"arXiv:2106.04520"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01965"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25477"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_24"},{"key":"ref15","first-page":"17616","article-title":"Relative uncertainty learning for facial expression recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Zhang"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00693"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680623"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.369"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01219"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01378-z"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00620"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01034"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00759"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01266"},{"key":"ref25","article-title":"FG-Net: Facial action unit detection with generalizable pyramidal features","author":"Yin","year":"2023","journal-title":"arXiv:2308.12380"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01897"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICME59968.2025.11209184"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561252"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3135516"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.07.028"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.03.036"},{"key":"ref32","first-page":"14338","article-title":"Knowledge augmented deep neural networks for joint facial expression and action unit recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Cui"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956650"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.02.011"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-10836-w"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00626"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0940-3"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475391"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2740923"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2014.06.002"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2013.4"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00608"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8802914"},{"key":"ref47","first-page":"596","article-title":"FixMatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sohn"},{"key":"ref48","first-page":"18408","article-title":"FlexMatch: Boosting semi-supervised learning with curriculum pseudo labeling","volume-title":"Proc. NIPS","author":"Zhang"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00413"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3247907"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3627418"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3204444"},{"key":"ref55","article-title":"CLIPER: A unified vision-language framework for in-the-wild facial expression recognition","author":"Li","year":"2023","journal-title":"arXiv:2303.00193"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72973-7_25"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3460538"},{"key":"ref58","article-title":"Cross-resolution face recognition via prior-aided face hallucination and residual knowledge distillation","author":"Kong","year":"2019","journal-title":"arXiv:1905.10777"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref60","volume-title":"DLIB-ML: A Machine Learning Toolkit","author":"King","year":"2009"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.3390\/biomimetics8020199"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00037"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00089"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/FG59268.2024.10581982"},{"key":"ref65","article-title":"Visual large language models for generalized and specialized applications","author":"Li","year":"2025","journal-title":"arXiv:2501.02765"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3582389"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02722"},{"key":"ref68","article-title":"GPT-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv:2303.08774"},{"key":"ref69","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv:2312.11805"},{"key":"ref70","article-title":"Qwen2.5-VL technical report","author":"Bai","year":"2025","journal-title":"arXiv:2502.13923"},{"key":"ref71","article-title":"EmotionHallucer: Evaluating emotion hallucinations in multimodal large language models","author":"Xing","year":"2025","journal-title":"arXiv:2505.11405"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2886767"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3093397"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3122146"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_14"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00148"},{"key":"ref77","article-title":"Ada-DF: An adaptive label distribution fusion network for facial expression recognition","author":"Liu","year":"2024","journal-title":"arXiv:2404.15714"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018594"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01977"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00596"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01918"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/173"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3257542"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02258-6"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/FG52635.2021.9667048"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2019.8756631"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681287"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01814"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11456304.pdf?arnumber=11456304","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:59:23Z","timestamp":1775505563000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11456304\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":91,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3675883","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}