{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T09:25:01Z","timestamp":1775208301094,"version":"3.50.1"},"reference-count":93,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Chinese National Natural Science Foundation Projects","doi-asserted-by":"publisher","award":["62276254"],"award-info":[{"award-number":["62276254"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Chinese National Natural Science Foundation Projects","doi-asserted-by":"publisher","award":["U2003111"],"award-info":[{"award-number":["U2003111"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Chinese National Natural Science Foundation Projects","doi-asserted-by":"publisher","award":["62176256"],"award-info":[{"award-number":["62176256"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Chinese National Natural Science Foundation Projects","doi-asserted-by":"publisher","award":["62106264"],"award-info":[{"award-number":["62106264"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L221013"],"award-info":[{"award-number":["L221013"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Youth Innovation Promotion Association Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["Y2021131"],"award-info":[{"award-number":["Y2021131"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"name":"InnoHK Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tifs.2023.3322600","type":"journal-article","created":{"date-parts":[[2023,10,6]],"date-time":"2023-10-06T17:49:37Z","timestamp":1696614577000},"page":"265-279","source":"Crossref","is-referenced-by-count":12,"title":["Masked Face Transformer"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3957-8590","authenticated-orcid":false,"given":"Weisong","family":"Zhao","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4636-9677","authenticated-orcid":false,"given":"Xiangyu","family":"Zhu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Kaiwen","family":"Guo","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8846-1853","authenticated-orcid":false,"given":"Haichao","family":"Shi","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1630-6058","authenticated-orcid":false,"given":"Xiao-Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0791-189X","authenticated-orcid":false,"given":"Zhen","family":"Lei","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-85729-932-1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.112"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_44"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2020.3047274"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.6028\/nist.ir.8311"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/app11052070"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2023.3242085"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108398"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/FG52635.2021.9667088"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00165"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IJCB52358.2021.9484337"},{"key":"ref12","article-title":"Learning face representation from scratch","author":"Yi","year":"2014","journal-title":"arXiv:1411.7923"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_6"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3478324"},{"key":"ref16","first-page":"1","article-title":"Masked face recognition for secure authentication","volume":"abs\/2008.11104","author":"Anwar","year":"2020","journal-title":"CoRR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref21","first-page":"1","article-title":"Stand-alone self-attention in vision models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Ramachandran"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00356"},{"key":"ref23","first-page":"1","article-title":"Intriguing properties of vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Naseer"},{"key":"ref24","first-page":"1","article-title":"How do vision transformers work?","volume":"abs\/2202.06709","author":"Park","year":"2022","journal-title":"CoRR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref26","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. 8th Int. Conf. Learn. Represent.","author":"Zhu"},{"key":"ref27","article-title":"MSG-transformer: Exchanging local spatial information by manipulating messenger tokens","author":"Fang","year":"2021","journal-title":"arXiv:2105.15168"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_7"},{"key":"ref29","article-title":"CSWin transformer: A general vision transformer backbone with cross-shaped windows","author":"Dong","year":"2021","journal-title":"arXiv:2107.00652"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108522"},{"key":"ref31","first-page":"1","article-title":"MLFW: A database for face recognition on masked faces","volume":"abs\/2109.05804","author":"Wang","year":"2021","journal-title":"CoRR"},{"key":"ref32","first-page":"1","article-title":"Masked face recognition dataset and application","volume":"abs\/2003.09093","author":"Wang","year":"2020","journal-title":"CoRR"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413723"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413960"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2020.2967754"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00486"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3098962"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413731"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/FG52635.2021.9667081"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3390\/app11167310"},{"key":"ref41","article-title":"Boosting masked face recognition with multi-task ArcFace","author":"Montero","year":"2021","journal-title":"arXiv:2104.09874"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00835"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3109463"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00944"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3170246"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"ref47","first-page":"1988","article-title":"Deep learning face representation by joint identification-verification","volume-title":"Proc. Adv. Neural Inf. Process. Syst., Annu. Conf. Neural Inf. Process. Syst.","volume":"27","author":"Sun"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24261-3_7"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00552"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00594"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref53","first-page":"74","article-title":"HOTR: End-to-end human-object interaction detection with transformers","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Kim"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref56","first-page":"4055","article-title":"Image transformer","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Parmar"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.232"},{"key":"ref58","article-title":"Generating long sequences with sparse transformers","author":"Child","year":"2019","journal-title":"arXiv:1904.10509"},{"key":"ref59","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv:2004.05150"},{"key":"ref60","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chu"},{"key":"ref61","article-title":"Shuffle transformer: Rethinking spatial shuffle for vision transformer","author":"Huang","year":"2021","journal-title":"arXiv:2106.03650"},{"key":"ref62","first-page":"1","article-title":"Reformer: The efficient transformer","volume-title":"Proc. 7th Int. Conf. Learn. Represent.","author":"Kitaev"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00353"},{"key":"ref64","article-title":"BOAT: Bilateral local attention vision transformer","author":"Yu","year":"2022","journal-title":"arXiv:2201.13027"},{"key":"ref65","first-page":"9438","article-title":"Sparse sinkhorn attention","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Tay"},{"key":"ref66","first-page":"1","article-title":"Cross attention network for few-shot classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Hou"},{"key":"ref67","article-title":"Learning to propagate labels: Transductive propagation network for few-shot learning","author":"Liu","year":"2018","journal-title":"arXiv:1805.10002"},{"key":"ref68","article-title":"Mini-batch graphs for robust image classification","author":"Mondal","year":"2021","journal-title":"arXiv:2105.03237"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref70","article-title":"Few-shot learning with graph neural networks","author":"Garcia","year":"2017","journal-title":"arXiv:1711.04043"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1710.09412"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00753"},{"key":"ref75","article-title":"Invariant risk minimization","author":"Arjovsky","year":"2019","journal-title":"arXiv:1907.02893"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_8"},{"key":"ref77","first-page":"5102","article-title":"Domain agnostic learning with disentangled representations","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Peng"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00711"},{"key":"ref79","article-title":"BatchFormerV2: Exploring sample relationships for dense representation learning","author":"Hou","year":"2022","journal-title":"arXiv:2204.01254"},{"key":"ref80","article-title":"Cross-pose LFW: A database for studying cross-pose face recognition in unconstrained environments","author":"Zheng","year":"2018"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw.2017.250"},{"key":"ref82","first-page":"1","article-title":"Cross-age LFW: A database for studying cross-age face recognition in unconstrained environments","volume":"abs\/1708.08197","author":"Zheng","year":"2017","journal-title":"CoRR"},{"key":"ref83","first-page":"1","article-title":"Labeled faces in the wild: A database for studying face recognition in unconstrained environments","volume-title":"Proc. Workshop Faces Real-Life Images, Detection, Alignment, Recognit.","author":"Huang"},{"key":"ref84","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. 7th Int. Conf. Learn. Represent. (ICLR)","author":"Loshchilov"},{"key":"ref85","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. 38th Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Touvron"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531330"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.05.014"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11834"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00577"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.79"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2018.08.004"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1111\/1467-7687.00256"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00020"}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10206\/10319981\/10273410.pdf?arnumber=10273410","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T06:52:06Z","timestamp":1712904726000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10273410\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":93,"URL":"https:\/\/doi.org\/10.1109\/tifs.2023.3322600","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"value":"1556-6013","type":"print"},{"value":"1556-6021","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}