{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T21:58:04Z","timestamp":1784325484612,"version":"3.55.0"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2019YFA0706203"],"award-info":[{"award-number":["2019YFA0706203"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202139"],"award-info":[{"award-number":["62202139"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"University Synergy Innovation Program of Anhui Province","award":["GXXT-2022-038"],"award-info":[{"award-number":["GXXT-2022-038"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/taffc.2024.3453443","type":"journal-article","created":{"date-parts":[[2024,9,3]],"date-time":"2024-09-03T17:27:59Z","timestamp":1725384479000},"page":"624-638","source":"Crossref","is-referenced-by-count":60,"title":["From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-4436-6613","authenticated-orcid":false,"given":"Yin","family":"Chen","sequence":"first","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9446-249X","authenticated-orcid":false,"given":"Jia","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8348-392X","authenticated-orcid":false,"given":"Shiguang","family":"Shan","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3094-7735","authenticated-orcid":false,"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5461-3986","authenticated-orcid":false,"given":"Richang","family":"Hong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2017.7510622"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3141400"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2019.8756565"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413620"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2015.510"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475292"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.03.062"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109368"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25077"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icme57554.2024.10687508"},{"key":"ref13","article-title":"Prompting visual-language models for dynamic facial expression recognition","author":"Zhao","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612365"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.277"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2740923"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993165"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02025"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548190"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1037\/h0031619"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997632"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00610"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3423327.3423672"},{"key":"ref24","article-title":"Spatio-temporal transformer for dynamic facial expression recognition in the wild","author":"Ma","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00620"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00150"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref29","first-page":"16 664","article-title":"AdaptFormer: Adapting vision transformers for scalable visual recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref30","article-title":"Aim: Adapting image models for efficient video action recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang"},{"key":"ref31","first-page":"26 462","article-title":"ST-adapter: Parameter-efficient image-to-video transfer learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pan"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01282"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553734"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01471"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.3007327"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.341"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3124142"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2593719"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00339"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00620"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00626"},{"key":"ref42","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-97909-0_46"},{"key":"ref44","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref46","article-title":"Towards a unified view of parameter-efficient transfer learning","author":"He","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3263288"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00918"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01900"},{"key":"ref51","first-page":"25 005","article-title":"Visual prompting via image inpainting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bar"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01722"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/tcss.2024.3478839"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ASYU50717.2020.9259802"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref60","article-title":"PFLD: A practical facial landmark detector","author":"Guo","year":"2019"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00693"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_24"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00618"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00603"},{"key":"ref65","article-title":"MVT: Mask vision transformer for facial expression recognition in the wild","author":"Li","year":"2021"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3122146"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00358"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3226473"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3285231"},{"key":"ref70","article-title":"NR-DFERNet: Noise-robust network for dynamic facial expression recognition","author":"Li","year":"2022"},{"key":"ref71","first-page":"10 078","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tong"},{"issue":"11","key":"ref72","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5165369\/11018643\/10663980.pdf?arnumber=10663980","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T04:52:25Z","timestamp":1748667145000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10663980\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":72,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2024.3453443","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}