{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T05:46:04Z","timestamp":1777873564471,"version":"3.51.4"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100008868","name":"Jiangsu Province Department of Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008868","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002855","name":"Ministry of Science and Technology of the People's Republic of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002855","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.eswa.2026.131764","type":"journal-article","created":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T07:48:11Z","timestamp":1771573691000},"page":"131764","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Unsupervised anomaly detection with a stacked transformer diffusion reconstruction framework"],"prefix":"10.1016","volume":"315","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1179-6210","authenticated-orcid":false,"given":"Minjie","family":"Du","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9052-1543","authenticated-orcid":false,"given":"Hengyu","family":"Xu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7282-9133","authenticated-orcid":false,"given":"Fulin","family":"Shang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7381-1211","authenticated-orcid":false,"given":"Zheng","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7431-7957","authenticated-orcid":false,"given":"Yining","family":"Hu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7763-9492","authenticated-orcid":false,"given":"Lizhe","family":"Xie","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.131764_bib0001","series-title":"Asian conference on computer vision","first-page":"622","article-title":"GANomaly: Semi-supervised anomaly detection via adversarial training","author":"Akcay","year":"2018"},{"key":"10.1016\/j.eswa.2026.131764_bib0002","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"9592","article-title":"MVTec ad\u2013a comprehensive real-world dataset for unsupervised anomaly detection","author":"Bergmann","year":"2019"},{"key":"10.1016\/j.eswa.2026.131764_bib0003","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4183","article-title":"Uninformed students: Student-teacher anomaly detection with discriminative latent embeddings","author":"Bergmann","year":"2020"},{"key":"10.1016\/j.eswa.2026.131764_bib0004","doi-asserted-by":"crossref","unstructured":"Blattmann, A., Rombach, R., Oktay, K., & Ommer, B. (2022). Retrieval-augmented diffusion models. 10.48550\/ARXIV.2204.11824.","DOI":"10.52202\/068431-1114"},{"issue":"4","key":"10.1016\/j.eswa.2026.131764_bib0005","doi-asserted-by":"crossref","first-page":"3246","DOI":"10.1109\/TII.2024.3523574","article-title":"VarAD: Lightweight high-resolution image anomaly detection via visual autoregressive modeling","volume":"21","author":"Cao","year":"2025","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"10.1016\/j.eswa.2026.131764_bib0006","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/j.neunet.2021.12.008","article-title":"UTRAD: Anomaly detection and localization with u-transformer","volume":"147","author":"Chen","year":"2022","journal-title":"Neural Networks"},{"key":"10.1016\/j.eswa.2026.131764_bib0007","doi-asserted-by":"crossref","first-page":"221494","DOI":"10.1109\/ACCESS.2020.3043473","article-title":"Unsupervised anomaly detection using style distillation","volume":"8","author":"Chung","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.eswa.2026.131764_bib0008","series-title":"Markov chains","author":"Chung","year":"1967"},{"issue":"5","key":"10.1016\/j.eswa.2026.131764_bib0009","doi-asserted-by":"crossref","first-page":"1459","DOI":"10.3390\/s20051459","article-title":"Visual-based defect detection and classification approaches for industrial applications-a survey","volume":"20","author":"Czimmermann","year":"2020","journal-title":"Sensors"},{"key":"10.1016\/j.eswa.2026.131764_bib0010","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"571","article-title":"Few-shot defect image generation via defect-aware feature manipulation","volume":"vol. 37","author":"Duan","year":"2023"},{"key":"10.1016\/j.eswa.2026.131764_bib0011","article-title":"Automatic lip-reading classification using deep learning approaches and optimized quaternion meixner moments by GWO algorithm","volume":"304","author":"El Ogri","year":"2024","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.eswa.2026.131764_bib0012","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2025.108744","article-title":"A computer-assisted medical diagnosis system for cancer diseases based on quaternion orthogonal rademacher-fourier moments and deep learning","volume":"112","author":"El Ogri","year":"2026","journal-title":"Biomedical Signal Processing and Control"},{"key":"10.1016\/j.eswa.2026.131764_bib0013","article-title":"3D image recognition using new set of fractional-order legendre moments and deep neural networks","volume":"98","author":"El Ogri","year":"2021","journal-title":"Signal Processing: Image Communication"},{"key":"10.1016\/j.eswa.2026.131764_bib0014","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"16532","article-title":"Boosting fine-grained visual anomaly detection with coarse-knowledge-aware adversarial learning","volume":"vol. 39","author":"Fang","year":"2025"},{"key":"10.1016\/j.eswa.2026.131764_bib0015","series-title":"Proceedings of the computer vision and pattern recognition conference","first-page":"20405","article-title":"Dinomaly: The less is more philosophy in multi-class unsupervised anomaly detection","author":"Guo","year":"2025"},{"key":"10.1016\/j.eswa.2026.131764_bib0016","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"8472","article-title":"A diffusion-based framework for multi-class anomaly detection","volume":"vol. 38","author":"He","year":"2024"},{"key":"10.1016\/j.eswa.2026.131764_bib0017","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.eswa.2026.131764_bib0018","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.131764_bib0019","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"8526","article-title":"Anomalydiffusion: Few-shot anomaly image generation with diffusion model","volume":"vol. 38","author":"Hu","year":"2024"},{"key":"10.1016\/j.eswa.2026.131764_bib0020","unstructured":"Kingma, D. P., & Welling, M. (2013). Auto-encoding variational bayes. arXiv: 1312.6114."},{"key":"10.1016\/j.eswa.2026.131764_bib0021","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"9664","article-title":"CutPaste: Self-supervised learning for anomaly detection and localization","author":"Li","year":"2021"},{"key":"10.1016\/j.eswa.2026.131764_bib0022","series-title":"Proceedings of the computer vision and pattern recognition conference","first-page":"4766","article-title":"One-for-more: Continual diffusion model for anomaly detection","author":"Li","year":"2025"},{"key":"10.1016\/j.eswa.2026.131764_bib0023","doi-asserted-by":"crossref","first-page":"3388","DOI":"10.1109\/TIP.2019.2959741","article-title":"Multistage GAN for fabric defect detection","volume":"29","author":"Liu","year":"2019","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.eswa.2026.131764_bib0024","series-title":"Icassp 2024-2024 ieee international conference on acoustics, speech and signal processing (icassp)","first-page":"4120","article-title":"Mixed-attention auto encoder for multi-class industrial anomaly detection","author":"Liu","year":"2024"},{"issue":"1","key":"10.1016\/j.eswa.2026.131764_bib0025","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1007\/s11633-023-1459-z","article-title":"Deep industrial image anomaly detection: A survey","volume":"21","author":"Liu","year":"2024","journal-title":"Machine Intelligence Research"},{"key":"10.1016\/j.eswa.2026.131764_bib0026","unstructured":"Liu, Y., Zhuang, C., & Lu, F. (2021). Unsupervised two-stage anomaly detection. arXiv: 2103.11671."},{"key":"10.1016\/j.eswa.2026.131764_bib0027","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"20402","article-title":"SimpleNet: A simple network for image anomaly detection and localization","author":"Liu","year":"2023"},{"key":"10.1016\/j.eswa.2026.131764_bib0028","series-title":"Dagm german conference on pattern recognition","first-page":"181","article-title":"Anomaly detection with conditioned denoising diffusion models","author":"Mousakhan","year":"2024"},{"key":"10.1016\/j.eswa.2026.131764_bib0029","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"4195","article-title":"Scalable diffusion models with transformers","author":"Peebles","year":"2023"},{"key":"10.1016\/j.eswa.2026.131764_bib0030","series-title":"Proceedings of the AAAI conference on artificial intelligence","article-title":"FILM: Visual reasoning with a general conditioning layer","volume":"vol. 32","author":"Perez","year":"2018"},{"key":"10.1016\/j.eswa.2026.131764_bib0031","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10684","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"10.1016\/j.eswa.2026.131764_bib0032","series-title":"International conference on medical image computing and computer-assisted intervention","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.1016\/j.eswa.2026.131764_bib0033","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"14902","article-title":"Multiresolution knowledge distillation for anomaly detection","author":"Salehi","year":"2021"},{"key":"10.1016\/j.eswa.2026.131764_bib0034","unstructured":"Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv: 1409.1556."},{"key":"10.1016\/j.eswa.2026.131764_bib0035","unstructured":"Song, J., Meng, C., & Ermon, S. (2020). Denoising diffusion implicit models. arXiv: 2010.02502."},{"key":"10.1016\/j.eswa.2026.131764_bib0036","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1016\/j.patrec.2019.11.024","article-title":"Integrating prediction and reconstruction for anomaly detection","volume":"129","author":"Tang","year":"2020","journal-title":"Pattern Recognition Letters"},{"key":"10.1016\/j.eswa.2026.131764_bib0037","first-page":"1","article-title":"Deep learning for unsupervised anomaly localization in industrial images: A survey","volume":"71","author":"Tao","year":"2022","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"10.1016\/j.eswa.2026.131764_bib0038","series-title":"Advances in Neural Information Processing Systems","first-page":"4790","article-title":"Conditional image generation with pixelcnn decoders","volume":"29","author":"Van den Oord","year":"2016"},{"issue":"6","key":"10.1016\/j.eswa.2026.131764_bib0039","doi-asserted-by":"crossref","first-page":"6182","DOI":"10.1109\/TIE.2021.3094452","article-title":"Industrial image anomaly localization based on gaussian clustering of pretrained feature","volume":"69","author":"Wan","year":"2021","journal-title":"IEEE Transactions on Industrial Electronics"},{"key":"10.1016\/j.eswa.2026.131764_bib0040","series-title":"Proceedings of the computer vision and pattern recognition conference","first-page":"20416","article-title":"Distribution prototype diffusion learning for open-set supervised anomaly detection","author":"Wang","year":"2025"},{"key":"10.1016\/j.eswa.2026.131764_bib0041","doi-asserted-by":"crossref","unstructured":"Wang, G., Han, S., Ding, E., & Huang, D. (2021). Student-teacher feature pyramid matching for anomaly detection. arXiv: 2103.04257.","DOI":"10.5244\/C.35.349"},{"key":"10.1016\/j.eswa.2026.131764_bib0042","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"650","article-title":"AnoDDPM: Anomaly detection with denoising diffusion probabilistic models using simplex noise","author":"Wyatt","year":"2022"},{"key":"10.1016\/j.eswa.2026.131764_bib0043","unstructured":"Xu, X., Wang, Y., Huang, Y., Liu, J., Lei, X., Xie, G., Jiang, G., & Lu, Z. (2025). A survey on industrial anomalies synthesis. arXiv: 2502.16412."},{"key":"10.1016\/j.eswa.2026.131764_bib0044","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"3110","article-title":"Learning semantic context from normal samples for unsupervised anomaly detection","volume":"vol. 35","author":"Yan","year":"2021"},{"key":"10.1016\/j.eswa.2026.131764_bib0045","first-page":"4571","article-title":"A unified model for multi-class anomaly detection","volume":"35","author":"You","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.131764_bib0046","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","first-page":"8330","article-title":"Draem - a discriminatively trained reconstruction embedding for surface anomaly detection","author":"Zavrtanik","year":"2021"},{"key":"10.1016\/j.eswa.2026.131764_bib0047","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"8330","article-title":"Draem-a discriminatively trained reconstruction embedding for surface anomaly detection","author":"Zavrtanik","year":"2021"},{"key":"10.1016\/j.eswa.2026.131764_bib0048","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2020.107706","article-title":"Reconstruction by inpainting for visual anomaly detection","volume":"112","author":"Zavrtanik","year":"2021","journal-title":"Pattern Recognition"},{"issue":"8","key":"10.1016\/j.eswa.2026.131764_bib0049","doi-asserted-by":"crossref","first-page":"7140","DOI":"10.1109\/TPAMI.2025.3570494","article-title":"DiffusionAD: Norm-guided one-step denoising diffusion for anomaly detection","volume":"47","author":"Zhang","year":"2025","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.131764_bib0050","series-title":"European conference on computer vision","first-page":"392","article-title":"Spot-the-difference self-supervised pre-training for anomaly detection and segmentation","author":"Zou","year":"2022"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426006779?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426006779?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T18:03:02Z","timestamp":1777572182000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426006779"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":50,"alternative-id":["S0957417426006779"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.131764","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Unsupervised anomaly detection with a stacked transformer diffusion reconstruction framework","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.131764","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"131764"}}