{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T09:27:27Z","timestamp":1770802047801,"version":"3.50.0"},"reference-count":91,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372150"],"award-info":[{"award-number":["62372150"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2022ZD0160101"],"award-info":[{"award-number":["2022ZD0160101"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3659337","type":"journal-article","created":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T20:50:14Z","timestamp":1770238214000},"page":"1551-1566","source":"Crossref","is-referenced-by-count":0,"title":["Accurate Industrial Anomaly Detection and Localization Using Weakly-Supervised Residual Transformers"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9433-1833","authenticated-orcid":false,"given":"Hanxi","family":"Li","sequence":"first","affiliation":[{"name":"Jiangxi Normal University, Jiangxi, Nanchang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3411-3188","authenticated-orcid":false,"given":"Jingqi","family":"Wu","sequence":"additional","affiliation":[{"name":"Jiangxi Normal University, Jiangxi, Nanchang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0371-9921","authenticated-orcid":false,"given":"Deyin","family":"Liu","sequence":"additional","affiliation":[{"name":"Anhui University, Anhui, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6119-058X","authenticated-orcid":false,"given":"Lin Yuanbo","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Warwick, Coventry, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4417-614X","authenticated-orcid":false,"given":"Hao","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University, Zhejiang, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunhua","family":"Shen","sequence":"additional","affiliation":[{"name":"Zhejiang University, Zhejiang, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3142326"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3241579"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3325229"},{"key":"ref4","article-title":"InternImage: Exploring large-scale vision foundation models with deformable convolutions","author":"Wang","year":"2022","journal-title":"arXiv:2211.05778"},{"key":"ref5","article-title":"Image as a foreign language: BEiT pretraining for all vision and vision-language tasks","author":"Wang","year":"2022","journal-title":"arXiv:2208.10442"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00982"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISIE45552.2021.9576231"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68799-1_35"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.11.030"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19915"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01392"},{"key":"ref12","article-title":"FAPM: Fast adaptive patch memory for real-time industrial anomaly detection","author":"Kim","year":"2022","journal-title":"arXiv:2211.07381"},{"key":"ref13","article-title":"PNI: Industrial anomaly detection using position and neighborhood information","author":"Bae","year":"2022","journal-title":"arXiv:2211.12634"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1541\/ieejjia.21013871"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23919\/CCC55666.2022.9902712"},{"key":"ref16","first-page":"1","article-title":"Pushing the limits of fewshot anomaly detection in industry vision: Graphcore","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Xie"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.11.018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00867"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00433"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3323997"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_42"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3391014"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3531646"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3218587"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00951"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00381"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_18"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01169"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00724"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01562"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02346"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref33","article-title":"The MVTec 3D-AD dataset for unsupervised 3D anomaly detection and localization","author":"Bergmann","year":"2021","journal-title":"arXiv:2112.09045"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2021.103459"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02159"},{"key":"ref36","first-page":"1","article-title":"MixMatch: A holistic approach to semi-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Berthelot"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3314801"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01359"},{"key":"ref39","first-page":"1","article-title":"A novel local focusing mechanism for deepfake detection generalization","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC)","author":"Li"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00822"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.105835"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00257"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref46","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00090"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"ref49","first-page":"21898","article-title":"SOLQ: Segmenting objects by learning queries","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dong"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00089"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00305"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00729"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3216771"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118269"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2022.103689"},{"key":"ref56","article-title":"ReMixMatch: Semi-supervised learning with distribution alignment and augmentation anchoring","author":"Berthelot","year":"2019","journal-title":"arXiv:1911.09785"},{"key":"ref57","first-page":"596","article-title":"FixMatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Sohn"},{"key":"ref58","first-page":"1","article-title":"FreeMatch: Self-adaptive thresholding for semi-supervised learning","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2909549"},{"key":"ref60","first-page":"1","article-title":"Mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3186746"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3543037"},{"key":"ref64","first-page":"6582","article-title":"Weakly supervised instance segmentation using the bounding box tightness prior","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Hsu"},{"key":"ref65","first-page":"365","article-title":"Bounding boxes for weakly supervised segmentation: Global constraints get close to full supervision","volume-title":"Proc. 3rd Conf. Med. Imag. Deep Learn.","volume":"121","author":"Kervadec"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00267"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00188"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref70","article-title":"Target before shooting: Accurate anomaly detection and localization under one millisecond via cascade patch retrieval","author":"Li","year":"2023","journal-title":"arXiv:2308.06748"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref73","article-title":"Image data augmentation for deep learning: A survey","author":"Yang","year":"2022","journal-title":"arXiv:2204.08610"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-019-01476-x"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01580"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01321"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01954"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02348"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00776"},{"key":"ref81","first-page":"4571","article-title":"A unified model for multi-class anomaly detection","volume-title":"Proc. NeurIPS","author":"You"},{"key":"ref82","first-page":"1","article-title":"ReContrast: Domain-specific anomaly detection via contrastive reconstruction","volume-title":"Proc. NeurIPS","author":"Guo"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28690"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2274"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01900"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01668"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00307"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-020-00697-6"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00408"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00424"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_39"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11372619.pdf?arnumber=11372619","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T05:57:49Z","timestamp":1770789469000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11372619\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":91,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3659337","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}