{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T21:51:09Z","timestamp":1774043469879,"version":"3.50.1"},"reference-count":81,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3663923","type":"journal-article","created":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T21:00:17Z","timestamp":1771966817000},"page":"2802-2815","source":"Crossref","is-referenced-by-count":0,"title":["Unified Anomaly Detection via Multi-Scale Contrasted Memory"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4896-0081","authenticated-orcid":false,"given":"Lo\u00efc","family":"J\u00e9z\u00e9quel","sequence":"first","affiliation":[{"name":"Idemia Identity and Security France, Osny, France"}]},{"given":"Jean","family":"Beaudet","sequence":"additional","affiliation":[{"name":"Idemia Identity and Security France, Osny, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3029-4412","authenticated-orcid":false,"given":"Aymeric","family":"Histace","sequence":"additional","affiliation":[{"name":"ETIS Laboratory - ENSEA, CYU, CNRS, Cergy, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3498-3335","authenticated-orcid":false,"given":"Ngoc-Son","family":"Vu","sequence":"additional","affiliation":[{"name":"LIST3N, Université de Technologie de Troyes (UTT), Troyes, France"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00954"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01392"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_27"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02136"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00179"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01438"},{"key":"ref7","article-title":"Deep nearest neighbor anomaly detection","author":"Bergman","year":"2020","journal-title":"arXiv:2002.10445"},{"key":"ref8","article-title":"Constrained adaptive projection with pretrained features for anomaly detection","author":"Gui","year":"2021","journal-title":"arXiv:2112.02597"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25309"},{"key":"ref10","first-page":"15637","article-title":"Using self-supervised learning can improve model robustness and uncertainty","volume-title":"Proc. NeurIPS","author":"Hendrycks"},{"key":"ref11","article-title":"Classification-based anomaly detection for general data","volume-title":"Proc. ICLR","author":"Bergman"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00822"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3322604"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00381"},{"key":"ref15","article-title":"CSI: Novelty detection via contrastive learning on distributionally shifted instances","volume-title":"Proc. NeurIPS","author":"Tack"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01518"},{"key":"ref17","article-title":"Hopfield networks is all you need","volume-title":"Proc. ICLR","author":"Ramsauer"},{"key":"ref18","article-title":"A unified survey on anomaly, novelty, open-set, and out of-distribution detection: Solutions and future challenges","volume-title":"Trans. Mach. Learn. Res.","author":"Salehi","year":"2022"},{"key":"ref19","article-title":"A survey on visual anomaly detection: Challenge, approach, and prospect","author":"Cao","year":"2024","journal-title":"arXiv:2401.16402"},{"key":"ref20","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00724"},{"key":"ref22","article-title":"A unified model for multi-class anomaly detection","volume-title":"Proc. NeuRIPS","author":"You"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956420"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3231532"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/198"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/84"},{"key":"ref27","first-page":"12310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","volume-title":"Proc. ICML","author":"\u017dbontar"},{"key":"ref28","article-title":"Do we really need to learn representations from in-domain data for outlier detection?","author":"Xiao","year":"2021","journal-title":"arXiv:2105.09270"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00283"},{"key":"ref30","article-title":"SSD: A unified framework for self-supervised outlier detection","volume-title":"Proc. ICLR","author":"Sehwag"},{"key":"ref31","article-title":"Learning and evaluating representations for deep one-class classification","volume-title":"Proc. ICLR","author":"Sohn"},{"key":"ref32","article-title":"InFlow: Robust outlier detection utilizing normalizing flows","author":"Kumar","year":"2021","journal-title":"arXiv:2106.12894"},{"key":"ref33","article-title":"Deep variational semi-supervised novelty detection","author":"Daniel","year":"2019","journal-title":"arXiv:1911.04971"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00080"},{"key":"ref35","article-title":"Fake it till you make it: Near-distribution novelty detection by score-based generative models","volume-title":"Proc. ICLR","author":"Mirzaei"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00301"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00216"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-41404-7_12"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-59050-9_12"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506332"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00951"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00451"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.129"},{"key":"ref44","article-title":"Deep semi-supervised anomaly detection","volume-title":"Proc. ICLR","author":"Ruff"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956091"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.105835"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01878"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888834"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00447"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i6.42404"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27963"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00982"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539872"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69544-6_23"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01507"},{"key":"ref56","first-page":"18250","article-title":"Hybrid energy based model in the feature space for out-of-distribution detection","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lafon"},{"key":"ref57","article-title":"Extremely simple activation shaping for out-of-distribution detection","volume-title":"Proc. ICLR","author":"Djurisic"},{"key":"ref58","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. ICML","volume":"1","author":"Chen"},{"key":"ref59","article-title":"VICReg: Variance-invariance-covariance regularization for self-supervised learning","volume-title":"Proc. ICLR","author":"Bardes"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref63","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. NeurIPS","author":"Caron"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00945"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01016"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01434"},{"key":"ref67","article-title":"Out-of-distribution detection based on in-distribution data patterns memorization with modern Hopfield energy","volume-title":"Proc. ICLR","author":"Zhang"},{"key":"ref68","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref69","article-title":"Caltech-UCSD birds 200","volume-title":"California Institute of Technology","author":"Welinder","year":"2010"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2916652"},{"key":"ref71","article-title":"Reading digits in natural images with unsupervised feature learning","volume-title":"Proc. NIPS","author":"Netzer"},{"key":"ref72","article-title":"LSUN: Construction of a large-scale image dataset using deep learning with humans in the loop","author":"Yu","year":"2015","journal-title":"arXiv:1506.03365"},{"key":"ref73","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","volume-title":"Proc. ICML","author":"Sutskever"},{"key":"ref74","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00532"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00933"},{"key":"ref78","article-title":"Energy-based out-of-distribution detection","volume-title":"Proc. NeurIPS","author":"Liu"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01506"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01114"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11410053.pdf?arnumber=11410053","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T20:01:08Z","timestamp":1774036868000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11410053\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":81,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3663923","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}