{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T09:56:25Z","timestamp":1781776585185,"version":"3.54.5"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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":[{"name":"National Key R&D Program of China","award":["2022ZD0161901"],"award-info":[{"award-number":["2022ZD0161901"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276018"],"award-info":[{"award-number":["62276018"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"BUPT Kunpeng & Ascend Center of Cultivation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/taffc.2025.3610185","type":"journal-article","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T17:34:32Z","timestamp":1758044072000},"page":"176-189","source":"Crossref","is-referenced-by-count":2,"title":["Temporal Group Constrained Transformer With Deformable Landmark Attention for Video Dimensional Emotion Recognition"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5093-5635","authenticated-orcid":false,"given":"Weixin","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangjing","family":"Meng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0993-8495","authenticated-orcid":false,"given":"Linmei","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3121-9756","authenticated-orcid":false,"given":"Xuan","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2012.31"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00230"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3266302.3268997"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2868499"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/0092-6566(77)90037-X"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2012.07.006"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/bs7040066"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00469"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3367371"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1110"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2940224"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3037496"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2022.3233083"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2010.2044788"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461920"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3063609"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461963"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475292"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.08.043"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3353739"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553805"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00358"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00280-0"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.125822"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2944808"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2886767"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2956143"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3280530"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3331309"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3226473"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811634"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3423327.3423672"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-548"},{"key":"ref34","first-page":"4898","article-title":"Understanding the effective receptive field in deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Luo","year":"2016"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref36","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref37","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00198"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref41","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121929"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3518"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2018.12.039"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/FG57933.2023.10042638"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612286"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00896"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3157141"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811642"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988258"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133953"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.2307\/2532051"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00019"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2740923"},{"key":"ref63","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993165"},{"key":"ref65","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref66","article-title":"LRS3-TED: A large-scale dataset for visual speech recognition","author":"Afouras","year":"2018"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5165369\/11418735\/11165014.pdf?arnumber=11165014","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T20:53:18Z","timestamp":1772571198000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11165014\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":67,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2025.3610185","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}