{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:09:35Z","timestamp":1781586575965,"version":"3.54.5"},"reference-count":67,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00610","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"6309-6319","source":"Crossref","is-referenced-by-count":1,"title":["VLMDiff: Leveraging Vision-Language Models for Multi-Class Anomaly Detection with Diffusion"],"prefix":"10.1109","author":[{"given":"Samet","family":"Hicsonmez","sequence":"first","affiliation":[{"name":"University of Luxembourg Luxembourg,Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abd","family":"El Rahman Shabayek","sequence":"additional","affiliation":[{"name":"University of Luxembourg Luxembourg,Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Djamila","family":"Aouada","sequence":"additional","affiliation":[{"name":"University of Luxembourg Luxembourg,Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_39"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5220\/0007364500002108"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00982"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00424"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00495"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_4"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref10","article-title":"Sub-image anomaly detection with deep pyramid correspondences","author":"Cohen","year":"2020","journal-title":"CoRR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3282993"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68799-1_35"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00951"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_6"},{"key":"ref16","first-page":"2672","article-title":"Generative adversarial nets","author":"Goodfellow","year":"2014","journal-title":"NeurIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680685"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00188"},{"key":"ref19","article-title":"Mambaad: Exploring state space models for multi-class unsupervised anomaly detection","author":"He","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28690"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","first-page":"6840","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01878"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3193699"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01359"},{"key":"ref26","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref28","article-title":"Deepseek-v3 technical report","author":"Liu","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01954"},{"key":"ref30","article-title":"On diffusion modeling for anomaly detection","author":"Livernoche","year":"2024","journal-title":"ICLR"},{"key":"ref31","article-title":"Exposing outlier exposure: What can be learned from few, one, and zero outlier images","author":"Liznerski","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"ref32","article-title":"Generalized out-of-distribution detection and beyond in vision language model era: A survey","author":"Miyai","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/s18010209"},{"key":"ref34","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3439950"},{"key":"ref36","author":"Paszke","year":"2017","journal-title":"Automatic differentiation in pytorch"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/325334.325247"},{"key":"ref38","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01392"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.01.010"},{"key":"ref43","article-title":"Ai-enabled thermal monitoring of commercial (phev) li-ion pouch cells with feature-adapted unsupervised anomaly detection","author":"El Rahman Shabayek","year":"2025","journal-title":"Journal of Power Sources"},{"key":"ref44","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015","journal-title":"ICML"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02348"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02159"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00032"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16452-1_4"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00080"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01897"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.333"},{"key":"ref52","first-page":"1","article-title":"Glad: towards better reconstruction with global and local adaptive diffusion models for un-supervised anomaly detection","author":"Yao","year":"2024","journal-title":"ECCV"},{"key":"ref53","first-page":"4571","article-title":"A unified model for multi-class anomaly detection","volume":"35","author":"You","year":"2022","journal-title":"NeurIPS"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01753"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00822"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3570494"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/iccvw69036.2025.00373"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-026-02809-z"},{"key":"ref60","article-title":"Exploring plain vit reconstruction for multi-class unsupervised anomaly detection","author":"Zhang","year":"2025","journal-title":"CVIU"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00624"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00381"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01580"},{"key":"ref65","article-title":"Anomalyclip: Object-agnostic prompt learning for zero-shot anomaly detection","author":"Zhou","year":"2024","journal-title":"ICLR"},{"key":"ref66","first-page":"19769","article-title":"Segment everything everywhere all at once","volume":"36","author":"Zou","year":"2023","journal-title":"NeurIPS"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_23"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492546.pdf?arnumber=11492546","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:06:11Z","timestamp":1778047571000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492546\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00610","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}