{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T16:08:28Z","timestamp":1783613308796,"version":"3.55.0"},"reference-count":96,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"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":["62571466"],"award-info":[{"award-number":["62571466"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Xiamen","award":["3502Z202573073"],"award-info":[{"award-number":["3502Z202573073"]}]},{"name":"Unveiling and Leading Projects of Xiamen","award":["3502Z20241011"],"award-info":[{"award-number":["3502Z20241011"]}]},{"DOI":"10.13039\/501100001809","name":"Major Science and Technology Plan Project on the Future Industry Fields of Xiamen City","doi-asserted-by":"publisher","award":["3502Z20241027"],"award-info":[{"award-number":["3502Z20241027"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Major Science and Technology Plan Project on the Future Industry Fields of Xiamen City","doi-asserted-by":"publisher","award":["3502Z20241029"],"award-info":[{"award-number":["3502Z20241029"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tcsvt.2025.3632418","type":"journal-article","created":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:46:04Z","timestamp":1763059564000},"page":"4663-4677","source":"Crossref","is-referenced-by-count":2,"title":["CAMD: Context-Aware Masked Distillation for General Self-Supervised Facial Representation Pre-Training"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6616-5892","authenticated-orcid":false,"given":"Sensen","family":"Wang","sequence":"first","affiliation":[{"name":"Fujian Key Laboratory of Pattern Recognition and Image Understanding, School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5631-7942","authenticated-orcid":false,"given":"Si","family":"Chen","sequence":"additional","affiliation":[{"name":"Fujian Key Laboratory of Pattern Recognition and Image Understanding, School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5901-0778","authenticated-orcid":false,"given":"Da-Han","family":"Wang","sequence":"additional","affiliation":[{"name":"Fujian Key Laboratory of Pattern Recognition and Image Understanding, School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5536-503X","authenticated-orcid":false,"given":"Yang","family":"Hua","sequence":"additional","affiliation":[{"name":"Institute of Electronics, Communications and Information Technology, Queen’s University Belfast, Belfast, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3674-7160","authenticated-orcid":false,"given":"Yan","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3253799"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611999"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00826"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3113780"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00451"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.369"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3415112"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00945"},{"key":"ref10","article-title":"Learning deep representations by mutual information estimation and maximization","author":"Hjelm","year":"2018","journal-title":"arXiv:1808.06670"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00996"},{"key":"ref12","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2021","journal-title":"arXiv:2106.08254"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref14","article-title":"Benchmarking detection transfer learning with vision transformers","author":"Li","year":"2021","journal-title":"arXiv:2111.11429"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3470230"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"issue":"2","key":"ref21","first-page":"1","article-title":"Variance-invariancecovariance regularization for self-supervised learning","volume-title":"Proc. Int. Conf. Learn. Represent.","volume":"1","author":"Bardes"},{"key":"ref22","first-page":"12310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zbontar"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_26"},{"key":"ref25","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. NIPS","author":"Caron"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/200"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00203"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681287"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00937"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00598"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_7"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01814"},{"key":"ref33","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref35","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020","journal-title":"arXiv:2003.04297"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00946"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6622"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3272741"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00212"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref41","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. (ICML)","volume":"162","author":"Baevski"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3488098"},{"key":"ref43","article-title":"A simple, efficient and scalable contrastive masked autoencoder for learning visual representations","author":"Mishra","year":"2022","journal-title":"arXiv:2210.16870"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00954"},{"key":"ref45","article-title":"Revisiting self-supervised contrastive learning for facial expression recognition","author":"Shu","year":"2022","journal-title":"arXiv:2210.03853"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00975"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00637"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3442888"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3304724"},{"key":"ref50","article-title":"FaceXFormer: A unified transformer for facial analysis","author":"Narayan","year":"2024","journal-title":"arXiv:2403.12960"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02269"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00412"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02009"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/152"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01485"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-78104-9_26"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01787-w"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3056098"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3382618"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3378180"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00859"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/FG57933.2023.10042513"},{"key":"ref64","article-title":"SEED: Self-supervised distillation for visual representation","author":"Fang","year":"2021","journal-title":"arXiv:2101.04731"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref67","article-title":"FitNets: Hints for thin deep nets","author":"Romero","year":"2014","journal-title":"arXiv:1412.6550"},{"key":"ref68","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref69","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015","journal-title":"arXiv:1502.03167"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00020"},{"key":"ref71","first-page":"1","article-title":"VilBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lu"},{"key":"ref72","article-title":"iBOT: Image BERT pre-training with online tokenizer","author":"Zhou","year":"2021","journal-title":"arXiv:2111.07832"},{"key":"ref73","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32661"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00414"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6832"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_16"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00227"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2016.01.002"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.59"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2013.132"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00402"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993165"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.277"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3049955"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_24"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.23"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2969189"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01174"},{"key":"ref92","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01897"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00753"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00123"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00127"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11475579\/11245609.pdf?arnumber=11245609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T20:03:47Z","timestamp":1775592227000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11245609\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":96,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3632418","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}