{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T15:54:10Z","timestamp":1779292450151,"version":"3.51.4"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"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":["62431004"],"award-info":[{"award-number":["62431004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017683","name":"Dalian Science and Technology Innovation Foundation","doi-asserted-by":"publisher","award":["2023JJ12GX015"],"award-info":[{"award-number":["2023JJ12GX015"]}],"id":[{"id":"10.13039\/501100017683","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tcsvt.2024.3524784","type":"journal-article","created":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T19:49:28Z","timestamp":1735674568000},"page":"4883-4895","source":"Crossref","is-referenced-by-count":3,"title":["FocusCLIP: Focusing on Anomaly Regions by Visual-Text Discrepancies"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3723-1024","authenticated-orcid":false,"given":"Yuan","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3070-7501","authenticated-orcid":false,"given":"Jiayu","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9241-1688","authenticated-orcid":false,"given":"Lihe","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6668-9758","authenticated-orcid":false,"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00586"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01578-9"},{"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\/ICCV51070.2023.00599"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00097"},{"key":"ref7","article-title":"Sub-image anomaly detection with deep pyramid correspondences","author":"Cohen","year":"2020","journal-title":"arXiv:2005.02357"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68799-1_35"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00951"},{"key":"ref10","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01603"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27963"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00593"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00548"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_18"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02025"},{"key":"ref17","article-title":"Openclip","author":"Ilharco","year":"2021","journal-title":"Openclip"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01878"},{"key":"ref19","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01359"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00113"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01469"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3382633"},{"key":"ref25","first-page":"1","article-title":"Unsupervised discovery of steerable factors when graph deep generative models are entangled","volume":"21","author":"Liu","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01954"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01392"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01634"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00195"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_27"},{"key":"ref32","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Schuhmann"},{"key":"ref33","article-title":"LAION-400M: Open dataset of CLIP-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021","journal-title":"arXiv:2111.02114"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00838"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02348"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00383"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3420775"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3237562"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3327448"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-024-05283-7"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-024-03152-x"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69544-6_23"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3424435"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref47","article-title":"AnomalyCLIP: Object-agnostic prompt learning for zero-shot anomaly detection","author":"Zhou","year":"2023","journal-title":"arXiv:2310.18961"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01688"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_23"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10989278\/10819451.pdf?arnumber=10819451","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T04:21:28Z","timestamp":1746591688000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10819451\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":49,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3524784","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}