{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T09:25:02Z","timestamp":1775208302083,"version":"3.50.1"},"reference-count":90,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100015860","name":"Science and Technology Project of China Railway","doi-asserted-by":"publisher","award":["N2021X026"],"award-info":[{"award-number":["N2021X026"]}],"id":[{"id":"10.13039\/100015860","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tifs.2023.3280717","type":"journal-article","created":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T17:32:06Z","timestamp":1685381526000},"page":"3388-3400","source":"Crossref","is-referenced-by-count":13,"title":["Joint Holistic and Masked Face Recognition"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0776-3719","authenticated-orcid":false,"given":"Yuhao","family":"Zhu","sequence":"first","affiliation":[{"name":"Postgraduate Department, China Academy of Railway Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0126-1726","authenticated-orcid":false,"given":"Min","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing Normal University, Beijing, China"}]},{"given":"Hui","family":"Jing","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, China Academy of Railway Sciences, Beijing, China"}]},{"given":"Linlin","family":"Dai","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, China Academy of Railway Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4029-9935","authenticated-orcid":false,"given":"Zhenan","family":"Sun","sequence":"additional","affiliation":[{"name":"CRIPAC, NLPR, CASIA, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6432-7211","authenticated-orcid":false,"given":"Ping","family":"Li","sequence":"additional","affiliation":[{"name":"China Academy of Railway Sciences Corporation Ltd., Beijing, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-021-03150-3"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2977386"},{"key":"ref56","first-page":"15908","article-title":"Transformer in transformer","author":"han","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/app11167310"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/5591020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref53","article-title":"VRT: A video restoration transformer","author":"liang","year":"2022","journal-title":"arXiv 2201 12288"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2967754"},{"key":"ref55","article-title":"LocalViT: Bringing locality to vision transformers","author":"li","year":"2021","journal-title":"arXiv 2104 05707"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-020-02100-9"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108522"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3109463"},{"key":"ref19","first-page":"1","article-title":"An image is worth 16 ? 16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref18","article-title":"Boosting masked face recognition with multi-task ArcFace","author":"montero","year":"2021","journal-title":"arXiv 2104 09874"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref50","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","author":"xie","year":"2021","journal-title":"Proc NeurIPS"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_6"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IJCB52358.2021.9484337"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2023.3242085"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451704"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00165"},{"key":"ref42","article-title":"Face transformer for recognition","author":"zhong","year":"2021","journal-title":"arXiv 2103 14803"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.527"},{"key":"ref41","first-page":"1","article-title":"Part-based face recognition with vision transformers","author":"sun","year":"2022","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICB2018.2018.00033"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413731"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6869"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2014.7025068"},{"key":"ref49","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"zhu","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.6028\/NIST.IR.8331"},{"key":"ref7","first-page":"1","article-title":"The effect of wearing a mask on face recognition performance: An exploratory study","author":"damer","year":"2020","journal-title":"Proc Int Conf Biometrics Special Interest Group (BIOSIG)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-021-02050-w"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-10332-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506025"},{"key":"ref6","article-title":"Advice on the use of masks in the context of COVID-19: Interim guidance","author":"organization","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3423327.3423672"},{"key":"ref82","article-title":"Cross-pose LFW: A database for studying cross-pose face recognition in unconstrained environments","author":"zheng","year":"2018"},{"key":"ref81","article-title":"Cross-age LFW: A database for studying cross-age face recognition in unconstrained environments","author":"zheng","year":"2017","journal-title":"arXiv 1708 08197"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.87"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00078"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477558"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01035"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.250"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00166"},{"key":"ref78","article-title":"Labeled faces in the wild: Updates and new reporting procedures","author":"huang","year":"2014"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6906"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00401"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00552"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3478324"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01400"},{"key":"ref77","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","author":"sutskever","year":"2013","journal-title":"Proc 30th Int Conf Mach Learn"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00594"},{"key":"ref76","first-page":"1","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2019","journal-title":"Proc 7th Int Conf Learn Represent (ICLR)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3205018"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.03.007"},{"key":"ref39","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref71","article-title":"Gaussian error linear units (GELUs)","author":"hendrycks","year":"2016","journal-title":"arXiv 1606 08415"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref73","article-title":"DeepNet: Scaling transformers to 1,000 layers","author":"wang","year":"2022","journal-title":"arXiv 2203 00555"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref24","first-page":"4475","article-title":"Improving transformer optimization through better initialization","author":"huang","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1083"},{"key":"ref67","first-page":"38571","article-title":"Vitpose: Simple vision transformer baselines for human pose estimation","author":"xu","year":"2022","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref69","first-page":"1877","article-title":"Language models are few-shot learners","author":"brown","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.2478\/pralin-2018-0002"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref63","first-page":"1","article-title":"BEiT: BERT pre-training of image transformers","author":"bao","year":"2022","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.463"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1176"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"ref29","first-page":"180","article-title":"Softmax units for multinoulli output distributions","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"ref62","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"devlin","year":"2019","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2496947"}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10206\/9970396\/10138097.pdf?arnumber=10138097","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T18:01:01Z","timestamp":1688407261000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10138097\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":90,"URL":"https:\/\/doi.org\/10.1109\/tifs.2023.3280717","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"value":"1556-6013","type":"print"},{"value":"1556-6021","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}