{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T10:14:13Z","timestamp":1780395253853,"version":"3.54.1"},"reference-count":87,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022YFB3103500"],"award-info":[{"award-number":["2022YFB3103500"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302195"],"award-info":[{"award-number":["62302195"]}],"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":["62272200"],"award-info":[{"award-number":["62272200"]}],"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":["U22A2095"],"award-info":[{"award-number":["U22A2095"]}],"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":["61932010"],"award-info":[{"award-number":["61932010"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2022A1515011960"],"award-info":[{"award-number":["2022A1515011960"]}],"id":[{"id":"10.13039\/501100021171","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":[[2024,8]]},"DOI":"10.1109\/tcsvt.2024.3370668","type":"journal-article","created":{"date-parts":[[2024,2,26]],"date-time":"2024-02-26T20:14:25Z","timestamp":1708978465000},"page":"7467-7483","source":"Crossref","is-referenced-by-count":35,"title":["EViT: Privacy-Preserving Image Retrieval via Encrypted Vision Transformer in Cloud Computing"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8523-5391","authenticated-orcid":false,"given":"Qihua","family":"Feng","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9356-0861","authenticated-orcid":false,"given":"Peiya","family":"Li","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology, Jinan University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9994-0734","authenticated-orcid":false,"given":"Zhixun","family":"Lu","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology, Jinan University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9867-1712","authenticated-orcid":false,"given":"Chaozhuo","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0375-4459","authenticated-orcid":false,"given":"Zefan","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology, Jinan University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3934-2177","authenticated-orcid":false,"given":"Zhiquan","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology, Jinan University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9290-8272","authenticated-orcid":false,"given":"Chunhui","family":"Duan","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4294-0212","authenticated-orcid":false,"given":"Feiran","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology, Jinan University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4067-8230","authenticated-orcid":false,"given":"Jian","family":"Weng","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology, Jinan University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3491-5968","authenticated-orcid":false,"given":"Philip S.","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Illinois at Chicago, Chicago, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Deep image retrieval: A survey","author":"Chen","year":"2021","journal-title":"arXiv:2101.11282"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3080920"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2020.3038218"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023179"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ChinaSIP.2014.6889282"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2019.2927215"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2019.02688"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2019.03.021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-015-2741-z"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2016.06.016"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ARES.2015.18"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.109935"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9979814"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117508"},{"key":"ref15","first-page":"1839","article-title":"End-to-end learning for encrypted image retrieval","volume-title":"Proc. Asia\u2013Pacific Signal Inf. Process. Assoc. Annu. Summit Conf. (APSIPA ASC)","author":"Feng"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP56404.2022.10008861"},{"issue":"14","key":"ref17","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","volume-title":"Proc. 5th Berkeley Symp. Math. Statist. Probab.","volume":"1","author":"MacQueen"},{"key":"ref18","first-page":"1470","article-title":"Video Google: A text retrieval approach to object matching in videos","volume-title":"Proc. 9th IEEE Int. Conf. Comput. Vis. (ICCV)","author":"Zisserman"},{"key":"ref19","first-page":"478","article-title":"Unsupervised deep embedding for clustering analysis","volume-title":"Proc. Conf. Mach. Learn. (ICML)","volume":"48","author":"Xie"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref22","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2003","journal-title":"arXiv:2003.04297"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_16"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01348"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01187"},{"key":"ref27","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref29","first-page":"23296","article-title":"Intriguing properties of vision transformers","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Naseer"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2014.2365998"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2010.39"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2587258"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3492705"},{"key":"ref34","volume-title":"JPEG: Still Image Data Compression Standard","author":"Pennebaker","year":"1992"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/357744.357757"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2929068"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2917234"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3203247"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3032402"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3114209"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19930"},{"key":"ref44","article-title":"Self-supervised learning with Swin Transformers","author":"Xie","year":"2105","journal-title":"arXiv:2105.04553"},{"key":"ref45","article-title":"SiT: Self-supervised vision transformer","author":"Ahmed","year":"2021","journal-title":"arXiv:2104.03602"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref47","first-page":"140:1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-021-10528-4"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00014"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00198"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3176055"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3248791"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref60","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2023.3286119"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2017.2669999"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/SRDS.2015.27"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2316154"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-38980-1_8"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2786860"},{"key":"ref68","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref69","article-title":"Deep learning using rectified linear units (ReLU)","author":"Agarap","year":"2018","journal-title":"arXiv:1803.08375"},{"key":"ref70","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. 26th Annu. Conf. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref71","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Lear. (ICML)","volume":"139","author":"Touvron"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1670"},{"key":"ref74","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref77","article-title":"Large-scale landmark retrieval\/recognition under a noisy and diverse dataset","author":"Ozaki","year":"2019","journal-title":"arXiv:1906.04087"},{"key":"ref78","article-title":"Google landmark recognition 2020 competition third place solution","author":"Ha","year":"2020","journal-title":"arXiv:2010.05350"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00061"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_31"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2003.1227984"},{"key":"ref83","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Paszke"},{"issue":"86","key":"ref84","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2817065"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2003.12.022"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10634006\/10445482.pdf?arnumber=10445482","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T17:44:51Z","timestamp":1723571091000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10445482\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":87,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3370668","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}