{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T00:57:38Z","timestamp":1760576258789,"version":"build-2065373602"},"reference-count":102,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Project of China","award":["2021ZD0110704"],"award-info":[{"award-number":["2021ZD0110704"]}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]},{"name":"Shanghai Qi Zhi Institute, and Shanghai Science and Technology Commission","award":["21511101200"],"award-info":[{"award-number":["21511101200"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tpami.2025.3526802","type":"journal-article","created":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T14:45:30Z","timestamp":1736433930000},"page":"2739-2753","source":"Crossref","is-referenced-by-count":1,"title":["Auto-Pairing Positives Through Implicit Relation Circulation for Discriminative Self-Learning"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4521-6369","authenticated-orcid":false,"given":"Bo","family":"Pang","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6218-0242","authenticated-orcid":false,"given":"Zhenyu","family":"Wei","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingli","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1533-8576","authenticated-orcid":false,"given":"Cewu","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref2","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref3","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref4","first-page":"5229","article-title":"Unsupervised 3D point cloud representation learning by triangle constrained contrast for autonomous driving","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Lu"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00966"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"Oord","key":"ref7"},{"key":"ref8","first-page":"6827","article-title":"What makes for good views for contrastive learning?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tian"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"article-title":"Palm: Scaling language modeling with pathways","year":"2022","author":"Chowdhery","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00267"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00190"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20100"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref21","first-page":"548","article-title":"Discriminative unsupervised feature learning with convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dosovitskiy"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01365"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00304"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00828"},{"key":"ref27","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Caron"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_16"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01404"},{"article-title":"Self-labelling via simultaneous clustering and representation learning","year":"2019","author":"Asano","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00672"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01614"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref34","first-page":"12310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","volume-title":"Proc. Int. Conf. Int. Conf. Mach. Learn.","author":"Zbontar"},{"article-title":"VICReg: Variance-invariance-covariance regularization for self-supervised learning","year":"2021","author":"Bardes","key":"ref35"},{"key":"ref36","first-page":"8799","article-title":"VICRegL: Self-supervised learning of local visual features","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bardes"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01403"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01058"},{"article-title":"iBOT: Image BERT pre-training with online tokenizer","year":"2021","author":"Zhou","key":"ref39"},{"article-title":"Contrastive masked autoencoders are stronger vision learners","year":"2022","author":"Huang","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_26"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01556"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01617"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01091"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01362"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00967"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00564"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20040"},{"issue":"14","key":"ref49","first-page":"71","article-title":"Dall-E: Creating images from text","volume":"8","author":"Reddy","year":"2021","journal-title":"UGC Care Group I. J."},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00105"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475458"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00825"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00647"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2022.3198244"},{"key":"ref55","first-page":"12546","article-title":"Contrastive learning of global and local features for medical image segmentation with limited annotations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chaitanya"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.1045"},{"article-title":"Learning from 2D: Contrastive pixel-to-point knowledge transfer for 3D pretraining","year":"2021","author":"Liu","key":"ref57"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01857"},{"key":"ref61","first-page":"24206","article-title":"VATT: Transformers for multimodal self-supervised learning from raw video, audio and text","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Akbari"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2022.100616"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01402"},{"key":"ref65","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Khosla"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00989"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"article-title":"The forward-forward algorithm: Some preliminary investigations","year":"2022","author":"Hinton","key":"ref68"},{"article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","year":"2023","author":"Li","key":"ref69"},{"article-title":"Llama: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref70"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01003"},{"key":"ref72","first-page":"499","article-title":"Cp2: Copy-paste contrastive pretraining for semantic segmentation","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Wang"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01641"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01609"},{"article-title":"Learning visual groups from co-occurrences in space and time","year":"2015","author":"Isola","key":"ref75"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00198"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00996"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00990"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00818"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"article-title":"Large batch training of convolutional networks","year":"2017","author":"You","key":"ref86"},{"article-title":"SGDR: Stochastic gradient descent with warm restarts","year":"2016","author":"Loshchilov","key":"ref87"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01009"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00328"},{"article-title":"CO\u02c63: Cooperative unsupervised 3D representation learning for autonomous driving","year":"2022","author":"Chen","key":"ref94"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_2"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_39"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00464"},{"article-title":"Self-supervised learning with swin transformers","year":"2021","author":"Xie","key":"ref100"},{"key":"ref101","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"article-title":"Opt: Open pre-trained transformer language models","year":"2022","author":"Zhang","key":"ref102"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10916529\/10835191.pdf?arnumber=10835191","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T17:36:35Z","timestamp":1760549795000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10835191\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":102,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3526802","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}