{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T16:26:24Z","timestamp":1791303984176,"version":"4.1.0"},"reference-count":62,"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\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2021ZD0113303"],"award-info":[{"award-number":["2021ZD0113303"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62432006"],"award-info":[{"award-number":["62432006"]}],"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":["62276159"],"award-info":[{"award-number":["62276159"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017684","name":"Fundamental Research Program of Shanxi Province","doi-asserted-by":"publisher","award":["202303021223004"],"award-info":[{"award-number":["202303021223004"]}],"id":[{"id":"10.13039\/501100017684","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":[[2025,1]]},"DOI":"10.1109\/tcsvt.2024.3457840","type":"journal-article","created":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T18:45:49Z","timestamp":1726080349000},"page":"219-231","source":"Crossref","is-referenced-by-count":4,"title":["Contrastive Learning With Enhancing Detailed Information for Pre-Training Vision Transformer"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6981-2993","authenticated-orcid":false,"given":"Zhuomin","family":"Liang","sequence":"first","affiliation":[{"name":"Institute of Intelligent Information Processing, Shanxi University, Taiyuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0380-2995","authenticated-orcid":false,"given":"Liang","family":"Bai","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Information Processing, Shanxi University, Taiyuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7192-4648","authenticated-orcid":false,"given":"Jinyu","family":"Fan","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Information Processing, Shanxi University, Taiyuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1496-8923","authenticated-orcid":false,"given":"Xian","family":"Yang","sequence":"additional","affiliation":[{"name":"Alliance Manchester Business School, The University of Manchester, Manchester, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5887-9327","authenticated-orcid":false,"given":"Jiye","family":"Liang","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Information Processing, Shanxi University, Taiyuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3277462"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01170"},{"key":"ref5","article-title":"Vision transformer adapter for dense predictions","volume-title":"Proc. 11th Int. Conf. Learn. Represent. (ICLR)","author":"Chen"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3222871"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3175605"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3307789"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00950"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref13","first-page":"12310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Zbontar"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3320444"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2020.3003048"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00393"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00975"},{"key":"ref22","first-page":"3015","article-title":"Whitening for self-supervised representation learning","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Ermolov"},{"key":"ref23","first-page":"2983","article-title":"Adversarial self-supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Kim"},{"key":"ref24","first-page":"17081","article-title":"Contrastive learning with adversarial examples","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3272741"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3300319"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01017"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6757"},{"key":"ref29","first-page":"8765","article-title":"Debiased contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Chuang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01681-x"},{"key":"ref31","first-page":"21798","article-title":"Hard negative mixing for contrastive learning","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Kalantidis"},{"key":"ref32","article-title":"Contrastive learning with hard negative samples","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Robinson"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00113"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01014"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01639-z"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3200671"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01614-8"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01656-y"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01559"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref41","article-title":"Pyramid self-attention polymerization learning for semi-supervised skeleton-based action recognition","author":"Xu","year":"2023","journal-title":"arXiv:2302.02327"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3247103"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25887"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref45","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Bao"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2019.2910151"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_7"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3307700"},{"key":"ref49","article-title":"Image BERT pre-training with online tokenizer","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhou"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3336525"},{"key":"ref51","article-title":"What do self-supervised vision transformers learn?","volume-title":"Proc. 11th Int. Conf. Learn. Represent. (ICLR)","author":"Park"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2022.3221611"},{"key":"ref53","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref54","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statist.","author":"Coates"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref56","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020","journal-title":"arXiv:2003.04297"},{"key":"ref57","article-title":"Large batch training of convolutional networks","author":"You","year":"2017","journal-title":"arXiv:1708.03888"},{"key":"ref58","article-title":"One weird trick for parallelizing convolutional neural networks","author":"Krizhevsky","year":"2014","journal-title":"arXiv:1404.5997"},{"key":"ref59","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","author":"Goyal","year":"2017","journal-title":"arXiv:1706.02677"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2956516"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2018.2844175"},{"key":"ref62","first-page":"15908","article-title":"Transformer in transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Han"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10857816\/10677373.pdf?arnumber=10677373","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T19:24:57Z","timestamp":1738265097000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10677373\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":62,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3457840","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}