{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T00:00:30Z","timestamp":1780617630288,"version":"3.54.1"},"reference-count":106,"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":["62276259"],"award-info":[{"award-number":["62276259"]}],"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":["62201572"],"award-info":[{"award-number":["62201572"]}],"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":["U21B2010"],"award-info":[{"award-number":["U21B2010"]}],"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":["62271083"],"award-info":[{"award-number":["62271083"]}],"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":["62306316"],"award-info":[{"award-number":["62306316"]}],"id":[{"id":"10.13039\/501100001809","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.2024.3436913","type":"journal-article","created":{"date-parts":[[2024,8,5]],"date-time":"2024-08-05T17:38:45Z","timestamp":1722879525000},"page":"405-422","source":"Crossref","is-referenced-by-count":23,"title":["SVFAP: Self-Supervised Video Facial Affect Perceiver"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7944-3458","authenticated-orcid":false,"given":"Licai","family":"Sun","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9477-0599","authenticated-orcid":false,"given":"Zheng","family":"Lian","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kexin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"He","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingyu","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyang","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1529-1552","authenticated-orcid":false,"given":"Bin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9344-6428","authenticated-orcid":false,"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/34.895976"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2018.2890471"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2366127"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3094362"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997632"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413620"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2830596"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811634"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3181736"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109368"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3014171"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3423327.3423672"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475292"},{"key":"ref14","article-title":"Spatio-temporal transformer for dynamic facial expression recognition in the wild","author":"Ma","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2981446"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2017.8273633"},{"key":"ref18","article-title":"The ambiguous world of emotion representation","author":"Sethu","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3090866"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref21","article-title":"A survey on masked autoencoder for self-supervised learning in vision and beyond","author":"Zhang","year":"2022"},{"key":"ref22","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref24","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tong"},{"key":"ref25","article-title":"Masked autoencoders as spatiotemporal learners","author":"Feichtenhofer","year":"2022"},{"key":"ref26","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02025"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548190"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547865"},{"key":"ref30","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref33","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25077"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref40","first-page":"1","article-title":"Unsupervised representation learning by predicting image rotations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Komodakis"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.79"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref43","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Caron"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref45","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref46","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2021","journal-title":"arXiv:2106.08254"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ACII52823.2021.9597460"},{"key":"ref48","article-title":"Self-supervised learning of a facial attribute embedding from video","author":"Wiles","year":"2018"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01118"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00954"},{"key":"ref51","first-page":"1","article-title":"Self-supervised learning for facial action unit recognition through temporal consistency","volume-title":"Proc. 31st Brit. Mach. Vis. Conf.","author":"Lu"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_7"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01814"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref55","first-page":"10 347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref61","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"ref62","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jaegle"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICDEW.2006.145"},{"key":"ref67","article-title":"MSAF: Multimodal split attention fusion","author":"Su","year":"2020"},{"key":"ref68","article-title":"A cross-modal fusion network based on self-attention and residual structure for multimodal emotion recognition","author":"Fu","year":"2021"},{"key":"ref69","first-page":"23 818","article-title":"Efficient training of visual transformers with small datasets","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref70","first-page":"1","article-title":"What makes instance discrimination good for transfer learning?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhao"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00331"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00289"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.03.062"},{"key":"ref74","article-title":"NR-DFERNet: Noise-robust network for dynamic facial expression recognition","author":"Li","year":"2022"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01722"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2019.8925444"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3216993"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3234777"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747278"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-009-0344-2"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2014.051215"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2553038"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803603"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2907271"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.3390\/sym11010052"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA47822.2019.8946025"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05557-4"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3101563"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25078"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2762299"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_28"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01309-y"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.217"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2951656"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107715"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_27"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_32"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3363710"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5165369\/10908445\/10623380.pdf?arnumber=10623380","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T18:34:27Z","timestamp":1741026867000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10623380\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":106,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2024.3436913","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}