{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T23:04:05Z","timestamp":1780009445948,"version":"3.53.1"},"reference-count":42,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Research and Development Program through the Development of Core Technologies for Railway Track Inspection Based on Railway-Specialized Robotics of Korea Railroad Research Institute","award":["PK26312A1"],"award-info":[{"award-number":["PK26312A1"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3689927","type":"journal-article","created":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T19:36:59Z","timestamp":1777923419000},"page":"69011-69023","source":"Crossref","is-referenced-by-count":0,"title":["De-FuSE\u2014Disentangled Frequency and Semantic Embeddings for Unified Vision Anomaly Detection"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1450-4149","authenticated-orcid":false,"given":"Mariam","family":"Ishtiaq","sequence":"first","affiliation":[{"name":"Railroad Physical AI Research Department, Korea Railroad Research Institute (KRRI), Uiwang, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4702-0960","authenticated-orcid":false,"given":"Jongun","family":"Won","sequence":"additional","affiliation":[{"name":"Railroad Physical AI Research Department, Korea Railroad Research Institute (KRRI), Uiwang, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-04984-1_31"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/s23073554"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s12083-025-02134-1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00982"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01900"},{"key":"ref6","article-title":"AD-DINOv3: Enhancing DINOv3 for zero-shot anomaly detection with anomaly-aware calibration","author":"Yuan","year":"2025","journal-title":"arXiv:2509.14084"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755635"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01668"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01901"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2025.061466"},{"key":"ref11","article-title":"ViP2-CLIP: Visual-perception prompting with unified alignment for zero-shot anomaly detection","author":"Yang","year":"2025","journal-title":"arXiv:2505.17692"},{"key":"ref12","article-title":"Unified unsupervised anomaly detection via matching cost filtering","author":"Zhang","year":"2025","journal-title":"arXiv:2510.03363"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW69036.2025.00158"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2025.3566311"},{"key":"ref15","article-title":"INP-Former++: Advancing universal anomaly detection via intrinsic normal prototypes and residual learning","author":"Luo","year":"2025","journal-title":"arXiv:2506.03660"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01971"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/s25072250"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01940"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0330"},{"key":"ref20","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref21","author":"Ishtiaq","year":"2026","journal-title":"Glocal-HAD: Hybrid Attention Decoder for Reconstruction-Based Vision Anomaly Detection Framework"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00136"},{"key":"ref23","article-title":"SuperAD: A training-free anomaly classification and segmentation method for CVPR 2025 VAND 3.0 workshop challenge track 1: Adapt & detect","author":"Zhang","year":"2025","journal-title":"arXiv:2505.19750"},{"key":"ref24","first-page":"1","article-title":"Registers in small vision transformers: A reproducibility study of vision transformers need registers","author":"Bach","year":"2025","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref25","article-title":"Vision transformers need registers","author":"Darcet","year":"2023","journal-title":"arXiv:2309.16588"},{"key":"ref26","first-page":"1","article-title":"Register and [CLS] tokens induce a decoupling of local and global features in large vits","volume-title":"Proc. 39th Annu. Conf. Neural Inf. Process. Syst.","author":"Lappe"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW69036.2025.00345"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72855-6_13"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_22"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2622"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-96868-6_57"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00357"},{"key":"ref33","article-title":"CosFormer: Rethinking softmax in attention","author":"Qin","year":"2022","journal-title":"arXiv:2202.08791"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3545659"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00988"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01366"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28310"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICUMT54235.2021.9631567"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_23"},{"key":"ref41","article-title":"FlowCLAS: Enhancing normalizing flow via contrastive learning for anomaly segmentation","author":"Lee","year":"2024","journal-title":"arXiv:2411.19888"},{"key":"ref42","article-title":"Generalist multi-class anomaly detection via distillation to two heterogeneous Student networks","author":"Park","year":"2025","journal-title":"arXiv:2509.24448"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11505868.pdf?arnumber=11505868","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T22:39:51Z","timestamp":1780007991000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11505868\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3689927","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}