{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T14:27:06Z","timestamp":1775744826567,"version":"3.50.1"},"reference-count":92,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021ZD0112001"],"award-info":[{"award-number":["2021ZD0112001"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61831005"],"award-info":[{"award-number":["61831005"]}],"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":["61971095"],"award-info":[{"award-number":["61971095"]}],"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":["62271119"],"award-info":[{"award-number":["62271119"]}],"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":[[2023,11]]},"DOI":"10.1109\/tcsvt.2023.3272741","type":"journal-article","created":{"date-parts":[[2023,5,3]],"date-time":"2023-05-03T18:53:46Z","timestamp":1683140026000},"page":"6924-6938","source":"Crossref","is-referenced-by-count":10,"title":["Disturbed Augmentation Invariance for Unsupervised Visual Representation Learning"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9043-2787","authenticated-orcid":false,"given":"Haoyang","family":"Cheng","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7481-095X","authenticated-orcid":false,"given":"Hongliang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2936-6340","authenticated-orcid":false,"given":"Qingbo","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0963-0311","authenticated-orcid":false,"given":"Heqian","family":"Qiu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9313-8428","authenticated-orcid":false,"given":"Xiaoliang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3016-2567","authenticated-orcid":false,"given":"Fanman","family":"Meng","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, China"}]},{"given":"Taijin","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01228"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3114209"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_9"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01366"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_35"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01378"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00637"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00797"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3118681"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00550"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3068834"},{"key":"ref54","article-title":"Unsupervised deep metric learning via auxiliary rotation loss","author":"cao","year":"2019","journal-title":"arXiv 1911 07072"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref16","first-page":"1","article-title":"Unsupervised representation learning by predicting image rotations","author":"gidaris","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref19","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Proc IEEE Int Conf ICML"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.434"},{"key":"ref51","first-page":"12614","article-title":"Implicit semantic data augmentation for deep networks","author":"wang","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.645"},{"key":"ref91","article-title":"The caltech-UCSD birds-200-2011 dataset","author":"wah","year":"2011"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298761"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref89","first-page":"2172","article-title":"InfoGAN: Interpretable representation learning by information maximizing generative adversarial nets","author":"chen","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref48","first-page":"1","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"radford","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_29"},{"key":"ref42","first-page":"1","article-title":"Learning deep representations by mutual information estimation and maximization","author":"hjelm","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref86","first-page":"1","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref41","first-page":"1","article-title":"Self-labelling via simultaneous clustering and representation learning","author":"asano","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref85","article-title":"AutoAugment: Learning augmentation policies from data","author":"cubuk","year":"2018","journal-title":"arXiv 1805 09501"},{"key":"ref44","first-page":"4182","article-title":"Data-efficient image recognition with contrastive predictive coding","author":"henaff","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref88","article-title":"Wasserstein GAN","author":"arjovsky","year":"2017","journal-title":"arXiv 1701 07875"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00978"},{"key":"ref87","first-page":"2642","article-title":"Conditional image synthesis with auxiliary classifier GANs","author":"odena","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn (ICML)"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3091620"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3063377"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3080928"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref40","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","author":"caron","year":"2020","journal-title":"Proc NIPS"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref80","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc 13th Eur Conf Comput Vis (ECCV)"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3130158"},{"key":"ref79","author":"wu","year":"2019","journal-title":"Detectron2"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2952550"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3124908"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3103782"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref75","article-title":"Large batch training of convolutional networks","author":"you","year":"2017","journal-title":"arXiv 1708 03888"},{"key":"ref30","first-page":"857","article-title":"Self-supervised learning: Generative or contrastive","volume":"35","author":"liu","year":"2023","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_38"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3003048"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01037"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01136"},{"key":"ref76","first-page":"4489","article-title":"Unsupervised learning of dense visual representations","author":"pinheiro","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","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":"ref1","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Annu Conf Adv Neural Inf Process Syst"},{"key":"ref39","first-page":"1","article-title":"Prototypical contrastive learning of unsupervised representations","author":"li","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00092"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00945"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11301"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01615"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01016"},{"key":"ref24","article-title":"The information bottleneck method","author":"tishby","year":"2000","journal-title":"arXiv physics\/0004057"},{"key":"ref68","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref67","article-title":"Improved baselines with momentum contrastive learning","author":"chen","year":"2020","journal-title":"arXiv 2003 04297"},{"key":"ref26","first-page":"1","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2013","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ITW.2015.7133169"},{"key":"ref69","first-page":"3630","article-title":"Matching networks for one shot learning","author":"vinyals","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1162\/089976603321780272"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2496141"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref66","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"2010","journal-title":"Proc IEEE Int Conf Mach Learn (ICML)"},{"key":"ref21","first-page":"21271","article-title":"Bootstrap your own latent—A new approach to self-supervised learning","author":"grill","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst Virtual"},{"key":"ref65","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref28","first-page":"4790","article-title":"Conditional image generation with PixelCNN decoders","author":"oord","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref27","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00728"},{"key":"ref62","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","author":"gutmann","year":"2010","journal-title":"Proc 13th Int Conf Artif Intell Statist"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10297951\/10114992.pdf?arnumber=10114992","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:41:59Z","timestamp":1699904519000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10114992\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11]]},"references-count":92,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3272741","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11]]}}}