{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T04:48:18Z","timestamp":1773550098428,"version":"3.50.1"},"reference-count":51,"publisher":"Association for Computing Machinery (ACM)","issue":"3","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62176027"],"award-info":[{"award-number":["62176027"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Chongqing Talent","award":["cstc2024ycjh-bgzxm0082"],"award-info":[{"award-number":["cstc2024ycjh-bgzxm0082"]}]},{"name":"Central University Operating Expenses","award":["2024CDJGF-044"],"award-info":[{"award-number":["2024CDJGF-044"]}]},{"DOI":"10.13039\/501100005230","name":"Natural Science Foundation of Chongqing","doi-asserted-by":"crossref","award":["CSTB2024NSCQ-MSX0479"],"award-info":[{"award-number":["CSTB2024NSCQ-MSX0479"]}],"id":[{"id":"10.13039\/501100005230","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Chongqing Postdoctoral Foundation","award":["2023CQBSHTB3119"],"award-info":[{"award-number":["2023CQBSHTB3119"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"crossref","award":["2024MD754244"],"award-info":[{"award-number":["2024MD754244"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2026,3,31]]},"abstract":"<jats:p>\n                    With the advancement of machine vision technology, automated vision inspection systems are needed in broad quality control scenarios. This article proposes a neighborhood attention-based feature reconstruction method for image anomaly detection and localization (NAFRAD). To address the challenges of data scarcity, low visibility, and irregular defect shapes in unsupervised anomaly detection, we introduce a feature reconstruction framework that preserves high-level abstract features rather than focusing on pixel-level reconstruction. This approach enhances model robustness and generalizability by leveraging neighborhood attention (NA) mechanisms, which simultaneously capture local details and the global context through a sliding window strategy. The NA-based autoencoder reconstructs normal features by aggregating local inductive biases with translational equivariance, enabling precise anomaly localization. Extensive experiments on the MVTec Anomaly Detection (MVTec AD) dataset\u2014comprising 15 categories with 5,354 images\u2014demonstrate the superiority of NAFRAD. It achieves state-of-the-art performance with AUROC\n                    <jats:inline-formula content-type=\"math\/tex\">\n                      <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\({}_{I}\\)<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    = 99.02, AUROC\n                    <jats:inline-formula content-type=\"math\/tex\">\n                      <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\({}_{P}\\)<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    = 98.99, and AP = 79.40, outperforming existing methods by 3.6% in AP and 0.89% in AUROC\n                    <jats:inline-formula content-type=\"math\/tex\">\n                      <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\({}_{P}\\)<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    . The framework\u2019s effectiveness is validated through ablation studies, visualization of feature reconstruction, and comparisons with eight leading unsupervised methods. The code is made public at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/Math-Computer\/NAFRAD\">https:\/\/github.com\/Math-Computer\/NAFRAD<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1145\/3786784","type":"journal-article","created":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T11:23:08Z","timestamp":1767612188000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Neighborhood Attention-based Feature Reconstruction for Image Anomaly Detection and Localization"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5137-3542","authenticated-orcid":false,"given":"Weizhi","family":"Xian","sequence":"first","affiliation":[{"name":"Chongqing Research Institute of Harbin Institute of Technology, Harbin Institute of Technology, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6938-2824","authenticated-orcid":false,"given":"Yichi","family":"Chen","sequence":"additional","affiliation":[{"name":"Chengdu Institute of Computer Application, Chinese Academy of Sciences, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3979-021X","authenticated-orcid":false,"given":"Bin","family":"Chen","sequence":"additional","affiliation":[{"name":"Chongqing Research Institute of Harbin Institute of Technology, Harbin Institute of Technology, Chongqing, China and Harbin Institute of Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5135-5165","authenticated-orcid":false,"given":"Leong Hou","family":"U","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Internet of Things for Smart City, University of Macau, Taipa,\u00a0Macao"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0670-1686","authenticated-orcid":false,"given":"Shiyou","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Chongqing University, Chongqing, China and Chongqing Tsingshan Industrial Co., Ltd., Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8820-8388","authenticated-orcid":false,"given":"Yong","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Computer Science, Chongqing University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1874-3641","authenticated-orcid":false,"given":"Mingliang","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science, Chongqing University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7484-7261","authenticated-orcid":false,"given":"Sam","family":"Kwong","sequence":"additional","affiliation":[{"name":"School of Data Sciences, Lingnan University, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,2,27]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00381"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00822"},{"key":"e_1_3_2_4_2","first-page":"1","article-title":"MixOOD: Improving out-of-distribution detection with enhanced data mixup","volume":"5","author":"Yang Taocun","year":"2023","unstructured":"Taocun Yang, Yaping Huang, Yanlin Xie, Junbo Liu, and Shengchun Wang. 2023. MixOOD: Improving out-of-distribution detection with enhanced data mixup. ACM Transactions on Multimedia Computing, Communications, and Applications 5 (2023), 1\u201318.","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2024.3431044"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2025.3588622"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3599097"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3630100"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2006.12.009"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2935153"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3205182"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3408034"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3341259"},{"key":"e_1_3_2_14_2","first-page":"1","article-title":"Unsupervised adversarial example detection of vision transformers for trustworthy edge computing","volume":"21","author":"Li Jiaxing","year":"2024","unstructured":"Jiaxing Li, Yu\u2019an Tan, Jie Yang, Zhengdao Li, Heng Ye, Chenxiao Xia, and Yuanzhang Li. 2024. Unsupervised adversarial example detection of vision transformers for trustworthy edge computing. ACM Transactions on Multimedia Computing, Communications, and Applications 21 (2024), 1\u201319.","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3237562"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2959741"},{"key":"e_1_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Wilson Tsang and Sam Kwong. 2005. Unsupervised anomaly intrusion detection using ant colony clustering model. In Soft Computing as Transdisciplinary Science and Technology 223\u2013232.","DOI":"10.1007\/3-540-32391-0_30"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3218587"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00057"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3335261"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3140070"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3420818"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/MIM.2020.9153576"},{"key":"e_1_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Zuzheng Wang Fouzi Harrou Ying Sun and Marc G. Genton. 2024. Exploring the magnitude-shape plot framework for anomaly detection in crowded video scenes. arXiv:2412.20363. Retrieved from https:\/\/arxiv.org\/abs\/2412.20363","DOI":"10.32388\/0N1EBC"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01676"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3586106"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2022.3215249"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02338-7"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2025.3609055"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2018.2886031"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3043473"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_29"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3046884"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1177\/0040517519862880"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00356"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00301"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00218"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3293772"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00599"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_43_2","doi-asserted-by":"crossref","unstructured":"Ali Hassani Wen-Mei Hwu and Humphrey Shi. 2024. Faster neighborhood attention: Reducing the O(n^2) cost of self attention at the threadblock level. In Advances in Neural Information Processing Systems Vol. 37 1\u201318.","DOI":"10.52202\/079017-2065"},{"key":"e_1_3_2_44_2","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","volume":"9351","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention (MICCAI), Vol. 9351, 234\u2013241.","journal-title":"Medical Image Computing and Computer-Assisted Intervention (MICCAI)"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00982"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68799-1_35"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01392"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01954"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3318302"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3314801"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3786784","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T03:49:01Z","timestamp":1773546541000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3786784"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,27]]},"references-count":51,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,3,31]]}},"alternative-id":["10.1145\/3786784"],"URL":"https:\/\/doi.org\/10.1145\/3786784","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,27]]},"assertion":[{"value":"2024-09-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-13","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}