{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T16:45:06Z","timestamp":1764175506924,"version":"3.37.3"},"reference-count":94,"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":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376266"],"award-info":[{"award-number":["62376266"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research Program of Frontier Sciences"},{"name":"CAS","award":["ZDBS-LY-7024"],"award-info":[{"award-number":["ZDBS-LY-7024"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3324588","type":"journal-article","created":{"date-parts":[[2023,10,13]],"date-time":"2023-10-13T18:06:26Z","timestamp":1697220386000},"page":"4628-4640","source":"Crossref","is-referenced-by-count":8,"title":["Beyond Instance Discrimination: Relation-Aware Contrastive Self-Supervised Learning"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9168-9231","authenticated-orcid":false,"given":"Yifei","family":"Zhang","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6747-0646","authenticated-orcid":false,"given":"Chang","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4188-9953","authenticated-orcid":false,"given":"Yu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8618-4992","authenticated-orcid":false,"given":"Weiping","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1215-6259","authenticated-orcid":false,"given":"Qixiang","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Electronic, Electrical, and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7333-9975","authenticated-orcid":false,"given":"Xiangyang","family":"Ji","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"ref3","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky","year":"2012"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2759500"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3004963"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2496141"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3115335"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_35"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref15","article-title":"Unsupervised representation learning by predicting image rotations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gidaris","year":"2018"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"Oord","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00637"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00537"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00252"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"article-title":"Improved baselines with momentum contrastive learning","year":"2020","author":"Chen","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1604.01685"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3151145"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.76"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref31","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Caron","year":"2020"},{"key":"ref32","first-page":"12310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zbontar","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01061"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01136"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.556"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00672"},{"key":"ref38","article-title":"Self-labelling via simultaneous clustering and representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Asano","year":"2020"},{"key":"ref39","article-title":"Prototypical contrastive learning of unsupervised representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2903628"},{"key":"ref41","first-page":"2849","article-title":"Unsupervised deep learning by neighbourhood discovery","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang","year":"2019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107107"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3054978"},{"key":"ref44","first-page":"3510","article-title":"Unsupervised representation learning by invariance propagation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2020"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00945"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3181116"},{"key":"ref47","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00692"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3127346"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3183586"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3137605"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"Hinton","key":"ref52"},{"key":"ref53","article-title":"Mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2018"},{"key":"ref54","article-title":"CO2: Consistent contrast for unsupervised visual representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wei","year":"2021"},{"key":"ref55","first-page":"2543","article-title":"ReSSL: Relational self-supervised learning with weak augmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zheng","year":"2021"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20119"},{"article-title":"A survey of mix-based data augmentation: Taxonomy, methods, applications, and explainability","year":"2022","author":"Cao","key":"ref57"},{"article-title":"Videomix: Rethinking data augmentation for video classification","year":"2020","author":"Yun","key":"ref58"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.285"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW58289.2023.00042"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.486"},{"key":"ref62","article-title":"Temporal ensembling for semi-supervised learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Laine","year":"2017"},{"key":"ref63","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tarvainen","year":"2017"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref66","article-title":"SEED: Self-supervised distillation for visual representation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fang","year":"2021"},{"key":"ref67","first-page":"5050","article-title":"Mixmatch: A holistic approach to semi-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Berthelot","year":"2019"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3158069"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00947"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3203630"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/504"},{"article-title":"Mixco: Mix-up contrastive learning for visual representation","year":"2020","author":"Kim","key":"ref72"},{"key":"ref73","first-page":"9929","article-title":"Understanding contrastive representation learning through alignment and uniformity on the hypersphere","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2020"},{"volume-title":"Information Theory and Statistics","year":"1959","author":"Kullback","key":"ref74"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00610"},{"key":"ref77","first-page":"5628","article-title":"A theoretical analysis of contrastive unsupervised representation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Saunshi","year":"2019"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015404"},{"key":"ref79","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Khosla","year":"2020"},{"key":"ref80","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref81","first-page":"21798","article-title":"Hard negative mixing for contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kalantidis","year":"2020"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00964"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01014"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01001"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01017"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00948"},{"key":"ref87","first-page":"6827","article-title":"What makes for good views for contrastive learning?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tian","year":"2020"},{"key":"ref88","article-title":"VICReg: Variance-invariance-covariance regularization for self-supervised learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bardes","year":"2022"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00113"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01000"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01556"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref92"},{"key":"ref93","first-page":"384","article-title":"Learning a parametric embedding by preserving local structure","volume":"5","author":"Maaten","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10285026.pdf?arnumber=10285026","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T18:50:04Z","timestamp":1710269404000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10285026\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":94,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3324588","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2024]]}}}