{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:05:53Z","timestamp":1783526753640,"version":"3.55.0"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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":["62236006"],"award-info":[{"award-number":["62236006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015401","name":"Key Research and Development Projects of Shaanxi Province","doi-asserted-by":"publisher","award":["2022ZDLGY06-03"],"award-info":[{"award-number":["2022ZDLGY06-03"]}],"id":[{"id":"10.13039\/501100015401","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/taffc.2024.3440924","type":"journal-article","created":{"date-parts":[[2024,8,9]],"date-time":"2024-08-09T17:24:51Z","timestamp":1723224291000},"page":"438-450","source":"Crossref","is-referenced-by-count":15,"title":["AVES: An Audio-Visual Emotion Stream Dataset for Temporal Emotion Detection"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5790-708X","authenticated-orcid":false,"given":"Yan","family":"Li","sequence":"first","affiliation":[{"name":"Shaanxi Key Laboratory on Speech and Image Information Processing, National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science, Northwestern Polytechnical University (NPU), Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Gan","sequence":"additional","affiliation":[{"name":"School of Engineering Science, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0176-3088","authenticated-orcid":false,"given":"Ke","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Engineering Science, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6238-8499","authenticated-orcid":false,"given":"Dongmei","family":"Jiang","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2373-4966","authenticated-orcid":false,"given":"Ramesh","family":"Jain","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of California, Irvine, Irvine, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1140.001.0001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3347320.3357688"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3347320.3357689"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3389\/fdgth.2022.933587"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119301"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3181736"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3141237"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00407"},{"key":"ref9","article-title":"Facial expression recognition with swin transformer","author":"Kim","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00264"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3395035.3425358"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.927665"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICDEW.2006.145"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1050"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413620"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02025"},{"key":"ref18","article-title":"Aff-wild2: Extending the aff-wild database for affect recognition","author":"Kollias","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01864"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2654440"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3174895"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548007"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"ref24","article-title":"MOSI: Multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos","author":"Zadeh","year":"2016"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2622690"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.8724"},{"key":"ref27","article-title":"SDFE-LV: A large-scale, multi-source, and unconstrained database for spotting dynamic facial expressions in long videos","author":"Xu","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-70353-4_46"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551608"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551602"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2012.26"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.02.022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2019.8.IMAWM-401"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506349"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2667642"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551601"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553717"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553799"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-558701-3.50007-7"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997638"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00056"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.593"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s10919-013-0159-8"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11031-011-9212-2"},{"key":"ref46","first-page":"1298","article-title":"Data2Vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Baevski"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref50","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612868"},{"key":"ref54","first-page":"10078","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"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2009.0141"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612358"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1015"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01667"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3672398"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321501"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681071"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5165369\/10908445\/10632787.pdf?arnumber=10632787","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T18:35:16Z","timestamp":1741026916000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10632787\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":63,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2024.3440924","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}