{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T15:36:26Z","timestamp":1786116986727,"version":"build-2736575974"},"reference-count":32,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T00:00:00Z","timestamp":1783382400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100018693","name":"Horizon Europe","doi-asserted-by":"publisher","award":["101133807"],"award-info":[{"award-number":["101133807"]}],"id":[{"id":"10.13039\/100018693","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition Letters"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.patrec.2026.07.005","type":"journal-article","created":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:13:18Z","timestamp":1783437198000},"page":"234-240","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Probabilistic image-based joint embedding predictive architecture"],"prefix":"10.1016","volume":"207","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4373-9081","authenticated-orcid":false,"given":"Lazaros","family":"Gogos","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dimitrios","family":"Katsikas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nikolaos","family":"Passalis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anastasios","family":"Tefas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patrec.2026.07.005_bib0001","article-title":"A path towards autonomous machine intelligence version 0.9. 2, 2022-06-27","volume":"62","author":"LeCun","year":"2022","journal-title":"Open Rev."},{"key":"10.1016\/j.patrec.2026.07.005_bib0002","series-title":"International Conference on Learning Representations","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.patrec.2026.07.005_bib0003","series-title":"Proceedings of the 37th International Conference on Machine Learning","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"10.1016\/j.patrec.2026.07.005_bib0004","series-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"15745","article-title":"Exploring simple siamese representation learning","author":"Chen","year":"2021"},{"key":"10.1016\/j.patrec.2026.07.005_bib0005","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"9726","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2020"},{"key":"10.1016\/j.patrec.2026.07.005_bib0006","series-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","article-title":"Bootstrap your own latent a new approach to self-supervised learning","author":"Grill","year":"2020"},{"key":"10.1016\/j.patrec.2026.07.005_bib0007","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"15979","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2022"},{"key":"10.1016\/j.patrec.2026.07.005_bib0008","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"15619","article-title":"Self-supervised learning from images with a joint-embedding predictive architecture","author":"Assran","year":"2023"},{"key":"10.1016\/j.patrec.2026.07.005_bib0009","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"9620","article-title":"An empirical study of training self-supervised vision transformers","author":"Chen","year":"2021"},{"key":"10.1016\/j.patrec.2026.07.005_bib0010","series-title":"2024 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI)","first-page":"1","article-title":"S3T: a new self-supervised learning with swin transformer","volume":"2","author":"Mazumdar","year":"2024"},{"key":"10.1016\/j.patrec.2026.07.005_bib0011","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"9630","article-title":"Emerging properties in self-supervised vision transformers","author":"Caron","year":"2021"},{"key":"10.1016\/j.patrec.2026.07.005_bib0012","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"8344","article-title":"Patch-level representation learning for self-supervised vision transformers","author":"Yun","year":"2022"},{"key":"10.1016\/j.patrec.2026.07.005_bib0013","series-title":"2023 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","first-page":"2777","article-title":"Multi-level contrastive learning for self-supervised vision transformers","author":"Mo","year":"2023"},{"key":"10.1016\/j.patrec.2026.07.005_bib0014","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.neunet.2023.05.037","article-title":"SCL: self-supervised contrastive learning for few-shot image classification","volume":"165","author":"Lim","year":"2023","journal-title":"Neural Netw."},{"key":"10.1016\/j.patrec.2026.07.005_bib0015","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.neunet.2022.09.028","article-title":"Robust image hashing for content identification through contrastive self-supervised learning","volume":"156","author":"Fonseca-Bustos","year":"2022","journal-title":"Neural Netw."},{"key":"10.1016\/j.patrec.2026.07.005_bib0016","series-title":"International Conference on Learning Representations","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2022"},{"key":"10.1016\/j.patrec.2026.07.005_bib0017","unstructured":"S.A.A. Ahmed, M. Awais, J. Kittler, SiT: self-supervised vision transformer, (2021). 2104.03602."},{"key":"10.1016\/j.patrec.2026.07.005_bib0018","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume":"Vol. 139","author":"Ramesh","year":"2021"},{"key":"10.1016\/j.patrec.2026.07.005_bib0019","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"9643","article-title":"SimMIM: a simple framework for masked image modeling","author":"Xie","year":"2022"},{"key":"10.1016\/j.patrec.2026.07.005_bib0020","series-title":"2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905)","first-page":"886","article-title":"Histograms of oriented gradients for human detection","volume":"Vol. 1","author":"Dalal","year":"2005"},{"key":"10.1016\/j.patrec.2026.07.005_bib0021","series-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems","article-title":"MST: masked self-supervised transformer for visual representation","author":"Li","year":"2021"},{"key":"10.1016\/j.patrec.2026.07.005_bib0022","series-title":"Proceedings of the 39th International Conference on Machine Learning","first-page":"20026","article-title":"Adversarial masking for self-supervised learning","volume":"Vol. 162","author":"Shi","year":"2022"},{"key":"10.1016\/j.patrec.2026.07.005_bib0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106817","article-title":"GO-MAE: self-supervised pre-training via masked autoencoder for OCT image classification of gynecology","volume":"181","author":"Wang","year":"2025","journal-title":"Neural Netw."},{"key":"10.1016\/j.patrec.2026.07.005_bib0024","series-title":"Proceedings of the International Conference on Machine Learning and Applications","first-page":"1111","article-title":"CNN-JEPA: self-supervised pretraining convolutional neural networks using joint embedding predictive architecture","author":"Kalapos","year":"2024"},{"issue":"5","key":"10.1016\/j.patrec.2026.07.005_bib0025","doi-asserted-by":"crossref","first-page":"2030","DOI":"10.1109\/TNNLS.2020.2995884","article-title":"Probabilistic knowledge transfer for lightweight deep representation learning","volume":"32","author":"Passalis","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.patrec.2026.07.005_bib0026","series-title":"Advances in Neural Information Processing Systems","first-page":"9164","article-title":"Learning efficient vision transformers via fine-grained manifold distillation","volume":"Vol. 35","author":"Hao","year":"2022"},{"key":"10.1016\/j.patrec.2026.07.005_bib0027","first-page":"1415","article-title":"Feature extraction by non-parametric mutual information maximization","volume":"3","author":"Torkkola","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.patrec.2026.07.005_bib0028","series-title":"Technical Report","article-title":"Learning Multiple Layers of Features from Tiny Images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.patrec.2026.07.005_bib0029","unstructured":"Intel, Intel Image Classification, 2018."},{"key":"10.1016\/j.patrec.2026.07.005_bib0030","series-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","author":"Coates","year":"2011"},{"key":"10.1016\/j.patrec.2026.07.005_bib0031","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"ImageNet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.patrec.2026.07.005_bib0032","unstructured":"J. Zhou, C. Wei, H. Wang, W. Shen, C. Xie, A. Yuille, T. Kong, iBOT: image BERT pre-training with online tokenizer, 2022. arxiv preprint arXiv: 2111.07832 [cs.CV]."}],"container-title":["Pattern Recognition Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167865526002357?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167865526002357?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T12:59:28Z","timestamp":1786021168000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167865526002357"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":32,"alternative-id":["S0167865526002357"],"URL":"https:\/\/doi.org\/10.1016\/j.patrec.2026.07.005","relation":{},"ISSN":["0167-8655"],"issn-type":[{"value":"0167-8655","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Probabilistic image-based joint embedding predictive architecture","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition Letters","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patrec.2026.07.005","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}]}}