{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:18:33Z","timestamp":1777889913972,"version":"3.51.4"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02245","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24224-24233","source":"Crossref","is-referenced-by-count":0,"title":["Kaputt: A Large-Scale Dataset for Visual Defect Detection"],"prefix":"10.1109","author":[{"given":"Sebastian","family":"H\u00f6fer","sequence":"first","affiliation":[{"name":"Amazon, Fulfillment Technologies & Robotics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dorian F.","family":"Henning","sequence":"additional","affiliation":[{"name":"Amazon, Fulfillment Technologies & Robotics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Artemij","family":"Amiranashvili","sequence":"additional","affiliation":[{"name":"Amazon, Fulfillment Technologies & Robotics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Douglas","family":"Morrison","sequence":"additional","affiliation":[{"name":"Amazon, Fulfillment Technologies & Robotics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mariliza","family":"Tzes","sequence":"additional","affiliation":[{"name":"Amazon, Fulfillment Technologies & Robotics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ingmar","family":"Posner","sequence":"additional","affiliation":[{"name":"Amazon, Fulfillment Technologies & Robotics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Matvienko","sequence":"additional","affiliation":[{"name":"Amazon, Fulfillment Technologies & Robotics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alessandro","family":"Rennola","sequence":"additional","affiliation":[{"name":"Amazon, Fulfillment Technologies & Robotics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anton","family":"Milan","sequence":"additional","affiliation":[{"name":"Amazon, Fulfillment Technologies & Robotics"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Agrawal","year":"2024","journal-title":"Pixtral 12b"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_39"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897283"},{"key":"ref4","year":"2024","journal-title":"The claude 3 model family: Opus, sonnet, haiku"},{"key":"ref5","first-page":"3","article-title":"Michael Fauser, David Sattlegger, and Carsten Steger","author":"Bergmann","year":"2018","journal-title":"Improving unsupervised defect segmentation by applying structural similarity to autoencoders"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01400-4"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72855-6_3"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2329"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01878"},{"key":"ref14","first-page":"8","author":"Jiang","year":"2025","journal-title":"MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3389\/fmolb.2021.614277"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92805-5_19"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISIE45552.2021.9576231"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160846"},{"key":"ref19","first-page":"6","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref20","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0551"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01392"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2019.08.002"},{"key":"ref25","first-page":"4393","article-title":"Deep one-class classification","volume-title":"International conference on machine learning","author":"Ruff"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.01.010"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3390\/app11020518"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-019-01476-x"},{"key":"ref29","first-page":"7","article-title":"Autogluon-multimodal (automm): Supercharging multimodal automl with foundation models","author":"Tang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73209-6_1"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69544-6_23"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2964055"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_23"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446177.pdf?arnumber=11446177","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:24:39Z","timestamp":1777613079000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446177\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02245","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}