{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T13:58:14Z","timestamp":1788271094865,"version":"build-2803163510"},"reference-count":74,"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\/wacv61042.2026.00360","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"3689-3699","source":"Crossref","is-referenced-by-count":3,"title":["Sea-CLIP: Mining Semantic-Aware Representations for Few-Shot Anomaly Detection with CLIP"],"prefix":"10.1109","author":[{"given":"Xiao","family":"Guo","sequence":"first","affiliation":[{"name":"Michigan State University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhimin","family":"Chen","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carlos D.","family":"Castillo","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongcheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoming","family":"Liu","sequence":"additional","affiliation":[{"name":"Michigan State University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"issue":"3","key":"ref1","first-page":"4","article-title":"Deep vit features as dense visual descriptors","volume":"2","author":"Amir","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00586"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112397"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00299"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00982"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00424"},{"key":"ref8","article-title":"Anomaly detection by adapting a pre-trained vision language model","author":"Cai","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_4"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-9003-6_2"},{"key":"ref12","article-title":"Sub-image anomaly detection with deep pyramid correspondences","author":"Cohen","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00136"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68799-1_35"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01603"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72855-6_26"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01503"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27963"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_13"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00593"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00308"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3711"},{"key":"ref25","article-title":"Language-guided hierarchical fine-grained image forgery detection and localization","author":"Guo","year":"2024","journal-title":"IJCV"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72855-6_13"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_18"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01878"},{"key":"ref30","article-title":"Language-driven semantic segmentation","author":"Li","year":"2022","journal-title":"ICLR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00954"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01594"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3374048"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01954"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref36","volume-title":"Mathematics for computer graphics applications.","author":"E Mortenson","year":"1999"},{"key":"ref37","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72890-7_18"},{"key":"ref39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on machine learning","author":"Radford"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref42","first-page":"2980","article-title":"Focal loss for dense object detection","volume-title":"proceedings of the IEEE Conference on computer vision and pattern recognition","author":"Ross"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01392"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01466"},{"key":"ref45","article-title":"Optimizing patchcore for few\/many-shot anomaly detection","author":"Santos","year":"2023"},{"key":"ref46","article-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2024.103958"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00838"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00310"},{"key":"ref50","article-title":"On learning multi-modal forgery representation for diffusion generated video detection","author":"Song","year":"2024","journal-title":"NeurIPS"},{"key":"ref51","article-title":"Pandagpt: One model to instruction-follow them all","author":"Su","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.349"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0358"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00433"},{"key":"ref55","article-title":"Clip-dinoiser: Teaching clip a few dino tricks","author":"Wysocza\u0144ska","year":"2023"},{"key":"ref56","article-title":"Pushing the limits of fewshot anomaly detection in industry vision: Graphcore","author":"Xie","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3979"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69544-6_23"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00822"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1973"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01416"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00624"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00381"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.737"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73223-2_22"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02023"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref72","article-title":"Anomalyclip: Object-agnostic prompt learning for zero-shot anomaly detection","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhou"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01688"},{"key":"ref74","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\/11492466.pdf?arnumber=11492466","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:12:17Z","timestamp":1778047937000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492466\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00360","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}