{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:04:45Z","timestamp":1784268285929,"version":"3.55.0"},"reference-count":61,"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":["62176065"],"award-info":[{"award-number":["62176065"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3709502","type":"journal-article","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T19:46:19Z","timestamp":1783626379000},"page":"7401-7414","source":"Crossref","is-referenced-by-count":0,"title":["Fine-Grained Enhancement Convolutional Diffusion Transformer for Unsupervised Anomaly Detection"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5449-7196","authenticated-orcid":false,"given":"Zeqi","family":"Ma","sequence":"first","affiliation":[{"name":"School of Automation, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8440-1765","authenticated-orcid":false,"given":"Xiaozhao","family":"Fang","sequence":"additional","affiliation":[{"name":"School of Automation and the Key Laboratory of Intelligent Detection and the Internet of Things in Manufacturing, Ministry of Education, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9208-1486","authenticated-orcid":false,"given":"Yue","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Automation, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9554-2379","authenticated-orcid":false,"given":"Jie","family":"Wen","sequence":"additional","affiliation":[{"name":"Bio-Computing Research Center, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1187-577X","authenticated-orcid":false,"given":"Guoxu","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Automation, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0530-2123","authenticated-orcid":false,"given":"Yong","family":"Xu","sequence":"additional","affiliation":[{"name":"Shenzhen Key Laboratory of Visual Object Detection and Recognition, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.124014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123423"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.124083"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2958826"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3057027"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02159"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00982"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01392"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68799-1_35"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3374048"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00822"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00954"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00951"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3293772"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3595408"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3381435"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0330"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28690"},{"key":"ref19","article-title":"Exploring plain ViT reconstruction for multi-class unsupervised anomaly detection","author":"Zhang","year":"2023","journal-title":"arXiv:2312.07495"},{"key":"ref20","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref24","article-title":"DINOv2: Learning robust visual features without supervision","volume-title":"Trans. Mach. Learn. Res.","author":"Oquab","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01954"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5244\/c.30.87"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28696"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3175611"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107706"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3279993"},{"key":"ref32","article-title":"Iterative energy-based projection on a normal data manifold for anomaly localization","volume-title":"Proc. Int. Conf. Learn. Represent","author":"Dehaene"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref35","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref37","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3543038"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2026.3671598"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.114784","article-title":"Nonconvex and adaptive multi-label learning for highly incomplete labels","volume":"331","author":"Luo","year":"2026","journal-title":"Knowl.-Based Syst."},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3559995"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0370"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00382"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2274"},{"key":"ref45","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv:2312.00752"},{"key":"ref46","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv:2210.02303"},{"key":"ref47","first-page":"19830","article-title":"Diffusiondet: Diffusion model for object detection","volume-title":"Proc. ICCV","author":"Chen"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3394777"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00381"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_23"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00408"},{"key":"ref52","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent","author":"Loshchilov"},{"key":"ref53","article-title":"Denoising diffusion implicit models","author":"Song","year":"2022","journal-title":"arXiv:2010.02502"},{"key":"ref54","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Touvron"},{"key":"ref55","first-page":"15979","article-title":"Masked autoencoders are scalable vision learners","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"He"},{"key":"ref56","article-title":"BEiT v2: Masked image modeling with vector-quantized visual tokenizers","author":"Peng","year":"2022","journal-title":"arXiv:2208.06366"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref59","article-title":"IBOT: Image BERT pre-training with online tokenizer","author":"Zhou","year":"2021","journal-title":"arXiv:2111.07832"},{"key":"ref60","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Tan"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11602734.pdf?arnumber=11602734","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T05:18:58Z","timestamp":1784265538000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11602734\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3709502","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}