{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T16:18:49Z","timestamp":1792858729017,"version":"4.5.0"},"reference-count":120,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001602","name":"Science Foundation Ireland through the Science Foundation Ireland (SFI) Centre for Research Training in Machine Learning","doi-asserted-by":"publisher","award":["18\/CRT\/6183"],"award-info":[{"award-number":["18\/CRT\/6183"]}],"id":[{"id":"10.13039\/501100001602","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Insight Centre for Data Analytics","award":["SFI\/12\/RC\/2289_P2"],"award-info":[{"award-number":["SFI\/12\/RC\/2289_P2"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3031549","type":"journal-article","created":{"date-parts":[[2020,10,16]],"date-time":"2020-10-16T15:45:59Z","timestamp":1602863159000},"page":"193907-193934","source":"Crossref","is-referenced-by-count":800,"title":["Contrastive Representation Learning: A Framework and Review"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0504-5844","authenticated-orcid":false,"given":"Phuc H.","family":"Le-Khac","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6429-6339","authenticated-orcid":false,"given":"Graham","family":"Healy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1028-8389","authenticated-orcid":false,"given":"Alan F.","family":"Smeaton","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref38","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":"ref33","article-title":"Watching the world go by: Representation learning from unlabeled videos","author":"gordon","year":"2020","journal-title":"arXiv 2003 07990"},{"key":"ref32","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume":"70","author":"gilmer","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref30","article-title":"COALA: Co-aligned autoencoders for learning semantically enriched audio representations","author":"favory","year":"2020","journal-title":"arXiv 2006 08386"},{"key":"ref37","first-page":"307","article-title":"Noise-contrastive estimation of unnormalized statistical models, with applications to natural image statistics","volume":"13","author":"gutmann","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref36","article-title":"Neural predictive belief representations","author":"guo","year":"2018","journal-title":"arXiv 1811 06407"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939754"},{"key":"ref34","article-title":"Bootstrap your own latent: A new approach to self-supervised learning","author":"grill","year":"2020","journal-title":"arXiv 2006 07733"},{"key":"ref28","article-title":"Whitening for self-supervised representation learning","author":"ermolov","year":"2020","journal-title":"arXiv 2007 06346"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593951"},{"key":"ref29","article-title":"CERT: Contrastive self-supervised learning for language understanding","author":"fang","year":"2020","journal-title":"arXiv 2005 12766"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"ref22","first-page":"2292","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","author":"cuturi","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"ref24","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"devlin","year":"2019","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol (NAACL-HLT)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref101","article-title":"What makes for good views for contrastive learning","author":"tian","year":"2020","journal-title":"arXiv 2005 10243"},{"key":"ref26","first-page":"766","article-title":"Discriminative unsupervised feature learning with convolutional neural networks","author":"dosovitskiy","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref100","article-title":"Contrastive representation distillation","author":"tian","year":"2019","journal-title":"arXiv 1910 10699"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.3160280102"},{"key":"ref50","article-title":"Probing text models for common ground with visual representations","author":"ilharco","year":"2020","journal-title":"arXiv 2005 00619"},{"key":"ref51","article-title":"Contrastive code representation learning","author":"jain","year":"2020","journal-title":"arXiv 2007 04973"},{"key":"ref59","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2016","journal-title":"arXiv 1609 02907"},{"key":"ref58","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014","journal-title":"arXiv 1312 6114"},{"key":"ref57","article-title":"CSTNet: Contrastive speech translation network for self-supervised speech representation learning","author":"khurana","year":"2020","journal-title":"arXiv 2006 02814"},{"key":"ref56","article-title":"Supervised contrastive learning","author":"khosla","year":"2020","journal-title":"arXiv 2004 11362"},{"key":"ref55","article-title":"Scaling laws for neural language models","author":"kaplan","year":"2020","journal-title":"arXiv 2001 08361"},{"key":"ref54","article-title":"Exploring the limits of language modeling","author":"jozefowicz","year":"2016","journal-title":"arXiv 1602 02410"},{"key":"ref53","article-title":"Self-supervised contrastive video-speech representation learning for ultrasound","author":"jiao","year":"2020","journal-title":"arXiv 2008 06607"},{"key":"ref52","article-title":"Categorical reparameterization with gumbel-softmax","author":"jang","year":"2016","journal-title":"arXiv 1611 01144"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00186"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref6","first-page":"1","article-title":"Vq-Wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref5","first-page":"15535","article-title":"Learning representations by maximizing mutual information across views","author":"bachman","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/355161a0"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24261-3_7"},{"key":"ref7","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"arXiv 2006 11477"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref46","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":"ref45","article-title":"In defense of the triplet loss for person re-identification","author":"hermans","year":"2017","journal-title":"arXiv 1703 07737"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref47","article-title":"Representation learning with video deep InfoMax","author":"hjelm","year":"2020","journal-title":"arXiv 2007 13278"},{"key":"ref42","article-title":"Deep residual learning for image recognition","author":"he","year":"2015","journal-title":"arXiv 1512 03385"},{"key":"ref41","first-page":"1","article-title":"Contrastive multi-view representation learning on graphs","author":"hassani","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref44","article-title":"Data-efficient image recognition with contrastive predictive coding","author":"h\u00e9naff","year":"2019","journal-title":"arXiv 1905 09272"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref73","first-page":"1","article-title":"Language agnostic speech embeddings for emotion classification","author":"nandan","year":"2020","journal-title":"Proc ICML Workshop SAS"},{"key":"ref72","article-title":"Audio-visual instance discrimination with cross-modal agreement","author":"morgado","year":"2020","journal-title":"arXiv 2004 12943"},{"key":"ref71","first-page":"1","article-title":"A fast and simple algorithm for training neural probabilistic language models","author":"mnih","year":"2012","journal-title":"Proc ICML"},{"key":"ref70","first-page":"2265","article-title":"Learning word embeddings efficiently with noise-contrastive estimation","author":"mnih","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref76","first-page":"73","article-title":"A discriminative language model with pseudo-negative samples","author":"okanohara","year":"2007","journal-title":"Proc 45th Annu Meeting Assoc Comput Linguistics"},{"key":"ref77","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018","journal-title":"arXiv 1807 03748"},{"key":"ref74","first-page":"271","article-title":"F-Gan: Training generative neural samplers using variational divergence minimization","author":"nowozin","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.434"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2000.857906"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref60","first-page":"1","article-title":"Contrastive learning of structured world models","author":"kipf","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref62","first-page":"34","article-title":"Loss functions for discriminative training of energy-based models","volume":"6","author":"lecun","year":"2005","journal-title":"Proc AISTATS"},{"key":"ref61","first-page":"1","article-title":"A mutual information maximization perspective of language representation learning","author":"kong","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref63","article-title":"Prototypical contrastive learning of unsupervised representations","author":"li","year":"2020","journal-title":"arXiv 2005 04966"},{"key":"ref64","article-title":"An efficient framework for learning sentence representations","author":"logeswaran","year":"2018","journal-title":"arXiv 1803 02893"},{"key":"ref65","first-page":"3039","article-title":"Putting an end to end-to-end: Gradient-isolated learning of representations","author":"l\u00f6we","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1405"},{"key":"ref67","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref68","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"arXiv 1301 3781 [cs]"},{"key":"ref2","first-page":"8769","article-title":"Unsupervised state representation learning in Atari","author":"anand","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"ref1","article-title":"Self-supervised learning of audio-visual objects from video","author":"afouras","year":"2020","journal-title":"arXiv 2008 04237"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.309"},{"key":"ref95","author":"stratos","year":"2019","journal-title":"Noise contrastive estimation"},{"key":"ref108","first-page":"1473","article-title":"Distance metric learning for large margin nearest neighbor classification","author":"weinberger","year":"2006","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref94","article-title":"Decoupling representation learning from reinforcement learning","author":"stooke","year":"2020","journal-title":"arXiv 2009 08319"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.320"},{"key":"ref93","article-title":"CURL: Contrastive unsupervised representations for reinforcement learning","author":"srinivas","year":"2020","journal-title":"arXiv 2004 04136"},{"key":"ref106","article-title":"Understanding contrastive representation learning through alignment and uniformity on the hypersphere","author":"wang","year":"2020","journal-title":"arXiv 2005 10242"},{"key":"ref92","first-page":"1857","article-title":"Improved deep metric learning with multi-class n-pair loss objective","author":"sohn","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.180"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"ref104","first-page":"1","article-title":"Deep graph infomax","author":"veli?kovi?","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref103","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref102","first-page":"1","article-title":"On mutual information maximization for representation learning","author":"tschannen","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref111","article-title":"What should not be contrastive in contrastive learning","author":"xiao","year":"2020","journal-title":"arXiv 2008 05659"},{"key":"ref112","article-title":"Delving into inter-image invariance for unsupervised visual representations","author":"xie","year":"2020","journal-title":"arXiv 2008 11702"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995538"},{"key":"ref99","article-title":"Contrastive multiview coding","author":"tian","year":"2019","journal-title":"arXiv 1906 05849"},{"key":"ref96","article-title":"Learning video representations using contrastive bidirectional transformer","author":"sun","year":"2019","journal-title":"arXiv 1906 05743"},{"key":"ref97","first-page":"1","article-title":"InfoGraph: Unsupervised and semi-supervised graph-level representation learning via mutual information maximization","author":"sun","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref10","first-page":"2787","article-title":"Translating embeddings for modeling multi-relational data","author":"bordes","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001493000339"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(91)90053-M"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref14","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","author":"caron","year":"2020","journal-title":"arXiv 2006 09882"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-02172-5_2"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.76"},{"key":"ref16","first-page":"1","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref82","article-title":"Online object representations with contrastive learning","author":"pirk","year":"2019","journal-title":"arXiv 1906 04312"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00637"},{"key":"ref17","article-title":"Big self-supervised models are strong semi-supervised learners","author":"chen","year":"2020","journal-title":"arXiv 2006 10029"},{"key":"ref81","article-title":"Multi-modal self-supervision from generalized data transformations","author":"patrick","year":"2020","journal-title":"arXiv 2003 04298"},{"key":"ref18","article-title":"InfoXLM: An information-theoretic framework for cross-lingual language model pre-training","author":"chi","year":"2020","journal-title":"arXiv 2007 07834"},{"key":"ref84","article-title":"Demystifying contrastive self-supervised learning: Invariances, augmentations and dataset biases","author":"purushwalkam","year":"2020","journal-title":"arXiv 2007 13916"},{"key":"ref119","article-title":"What makes instance discrimination good for transfer learning?","author":"zhao","year":"2020","journal-title":"arXiv 2006 06606"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref83","first-page":"5171","article-title":"On variational bounds of mutual information","author":"poole","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref114","article-title":"LoCo: Local contrastive representation learning","author":"xiong","year":"2020","journal-title":"arXiv 2008 01342"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref116","first-page":"5753","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","author":"yang","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref80","article-title":"Contrastive learning for unpaired image-to-image translation","author":"park","year":"2020","journal-title":"arXiv 2007 15651"},{"key":"ref115","article-title":"How powerful are graph neural networks?","author":"xu","year":"2018","journal-title":"arXiv 1810 00826"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00610"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403168"},{"key":"ref86","first-page":"3973","article-title":"Sentence-BERT: Sentence embeddings using siamese BERTNetworks","author":"reimers","year":"2019","journal-title":"Proc Conf Empirical Methods Natural Lang Process 9th Int Joint Conf Natural Lang Process (EMNLP-IJCNLP)"},{"key":"ref87","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref88","first-page":"5628","article-title":"A theoretical analysis of contrastive unsupervised representation learning","author":"arora","year":"2019","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09226466.pdf?arnumber=9226466","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,11]],"date-time":"2022-01-11T20:09:03Z","timestamp":1641931743000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9226466\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":120,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3031549","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}