{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T05:45:30Z","timestamp":1777873530836,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":62,"publisher":"ACM","funder":[{"name":"Institute of Information and Communications Technology Planning and Evaluation","award":["RS-2025-02219277"],"award-info":[{"award-number":["RS-2025-02219277"]}]},{"DOI":"10.13039\/501100006374","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2024-00345398,2340012392"],"award-info":[{"award-number":["RS-2024-00345398,2340012392"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"Korea Institute for Advancement of Technology","doi-asserted-by":"publisher","award":["RS-2025-02633871"],"award-info":[{"award-number":["RS-2025-02633871"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3737032","type":"proceedings-article","created":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T13:30:13Z","timestamp":1754055013000},"page":"1274-1285","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Logical Anomaly Detection with Text-based Logic via Component-Aware Contrastive Language-Image Training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3208-4882","authenticated-orcid":false,"given":"Seung-eon","family":"Lee","sequence":"first","affiliation":[{"name":"School of Undergraduate, DGIST, Daegu, Republic of Korea and ENERZAi, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8937-6263","authenticated-orcid":false,"given":"Soopil","family":"Kim","sequence":"additional","affiliation":[{"name":"Robots and Mechatronics Engineering, DGIST, Daegu, Republic of Korea and Division of Intelligent Robot, DGIST, Daegu, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3800-7158","authenticated-orcid":false,"given":"Sion","family":"An","sequence":"additional","affiliation":[{"name":"Robotics and Mechatronics Engineering, DGIST, Dalseong-gun, Daegu, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7209-1036","authenticated-orcid":false,"given":"Sang-Chul","family":"Lee","sequence":"additional","affiliation":[{"name":"Division of Nanotechnology, DGIST, Daegu, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7476-1046","authenticated-orcid":false,"given":"Sang Hyun","family":"Park","sequence":"additional","affiliation":[{"name":"Robotics and Mechatronics Engineering, DGIST, Daegu, Republic of Korea and The Interdisciplinary Studies of Artificial Intelligence, DGIST, Daegu, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.05.080"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00020"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01578-9"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00982"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00424"},{"key":"e_1_3_2_2_6_1","unstructured":"Yunkang Cao Xiaohao Xu Jiangning Zhang Yuqi Cheng Xiaonan Huang Guansong Pang and Weiming Shen. 2024. A survey on visual anomaly detection: Challenge approach and prospect. arXiv preprint arXiv:2401.16402(2024)."},{"key":"e_1_3_2_2_7_1","unstructured":"Xuhai Chen Yue Han and Jiangning Zhang. 2023. A zero-\/few-shot anomaly classification and segmentation method for cvpr 2023 vand workshop challenge tracks 1&2: 1st place on zero-shot ad and 4th place on few-shot ad. arXiv preprint arXiv:2305.17382(2023)."},{"key":"e_1_3_2_2_8_1","unstructured":"Niv Cohen Issar Tzachor and Yedid Hoshen. 2023. Set features for fine-grained anomaly detection. arXiv preprint arXiv:2302.12245(2023)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01603"},{"key":"e_1_3_2_2_10_1","unstructured":"Yao Fu Hao Peng Ashish Sabharwal Peter Clark and Tushar Khot. 2022. Complexity-based prompting for multi-step reasoning. arXiv preprint arXiv:2210.00720(2022)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27963"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1162"},{"key":"e_1_3_2_2_14_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Hsieh Cheng-Yu","year":"2024","unstructured":"Cheng-Yu Hsieh, Jieyu Zhang, Zixian Ma, Aniruddha Kembhavi, and Ranjay Krishna. 2024. Sugarcrepe: Fixing hackable benchmarks for vision-language compositionality. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_2_15_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685(2021).","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685(2021)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_18"},{"key":"e_1_3_2_2_17_1","unstructured":"Lei Huang Weijiang Yu Weitao Ma Weihong Zhong Zhangyin Feng Haotian Wang Qianglong Chen Weihua Peng Xiaocheng Feng Bing Qin et al. 2024. A survey on hallucination in large language models: Principles taxonomy challenges and open questions. ACM Transactions on Information Systems(2024)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-018-1588-5"},{"key":"e_1_3_2_2_19_1","volume-title":"Kyunghoon Bae, and Byung Jun Kang.","author":"Hyun Jeeho","year":"2023","unstructured":"Jeeho Hyun, Sangyun Kim, Giyoung Jeon, Seung Hwan Kim, Kyunghoon Bae, and Byung Jun Kang. 2023. ReConPatch: Contrastive Patch Representation Learning for Industrial Anomaly Detection. arXiv preprint arXiv:2305.16713(2023)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01878"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1123"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28703"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"crossref","unstructured":"Alexander Kirillov Eric Mintun Nikhila Ravi Hanzi Mao Chloe Rolland Laura Gustafson Tete Xiao Spencer Whitehead Alexander C Berg Wan-Yen Lo et al. 2023. Segment anything. arXiv preprint arXiv:2304.02643(2023).","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_2_24_1","volume-title":"Lisa: Reasoning segmentation via large language model. arXiv preprint arXiv:2308.00692(2023).","author":"Lai Xin","year":"2023","unstructured":"Xin Lai, Zhuotao Tian, Yukang Chen, Yanwei Li, Yuhui Yuan, Shu Liu, and Jiaya Jia. 2023. Lisa: Reasoning segmentation via large language model. arXiv preprint arXiv:2308.00692(2023)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01999"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3193699"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00954"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01594"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-023-1459-z"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2023.102161"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01169"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01050"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01367"},{"key":"e_1_3_2_2_35_1","volume-title":"Ref-diff: Zero-shot referring image segmentation with generative models. arXiv preprint arXiv:2308.16777(2023).","author":"Ni Minheng","year":"2023","unstructured":"Minheng Ni, Yabo Zhang, Kailai Feng, Xiaoming Li, Yiwen Guo, and Wangmeng Zuo. 2023. Ref-diff: Zero-shot referring image segmentation with generative models. arXiv preprint arXiv:2308.16777(2023)."},{"key":"e_1_3_2_2_36_1","unstructured":"OpenAI. 2024. ChatGPT: OpenAI Language Model. https:\/\/chat.openai.com\/. Version 4.0 Available at https:\/\/chat.openai.com\/."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00294"},{"key":"e_1_3_2_2_38_1","volume-title":"International conference on machine learning. PMLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748-8763."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01392"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00262"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00547"},{"key":"e_1_3_2_2_42_1","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann Christoph","year":"2022","unstructured":"Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, et al., 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. Advances in Neural Information Processing Systems, Vol. 35 (2022), 25278-25294.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_43_1","unstructured":"Robin Strudel Ivan Laptev and Cordelia Schmid. 2022. Weakly-supervised segmentation of referring expressions. arXiv preprint arXiv:2205.04725(2022)."},{"key":"e_1_3_2_2_44_1","volume-title":"Text Augmented Spatial Aware Zero-shot Referring Image Segmentation. In The 2023 Conference on Empirical Methods in Natural Language Processing.","author":"Suo Yucheng","year":"2023","unstructured":"Yucheng Suo, Linchao Zhu, and Yi Yang. 2023. Text Augmented Spatial Aware Zero-shot Referring Image Segmentation. In The 2023 Conference on Empirical Methods in Natural Language Processing."},{"key":"e_1_3_2_2_45_1","unstructured":"Niv Cohen Tzachor Yedid Hoshen et al. 2023. Set features for fine-grained anomaly detection. arXiv preprint arXiv:2302.12245(2023)."},{"key":"e_1_3_2_2_46_1","volume-title":"An overview of image caption generation methods. Computational intelligence and neuroscience","author":"Wang Haoran","year":"2020","unstructured":"Haoran Wang, Yue Zhang, and Xiaosheng Yu. 2020. An overview of image caption generation methods. Computational intelligence and neuroscience, Vol. 2020 (2020)."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01378"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"e_1_3_2_2_49_1","volume-title":"Denny Zhou, et al.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al., 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, Vol. 35 (2022), 24824-24837."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3371348"},{"key":"e_1_3_2_2_51_1","volume-title":"Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcore. In The Eleventh International Conference on Learning Representations.","author":"Xie Guoyang","year":"2022","unstructured":"Guoyang Xie, Jinbao Wang, Jiaqi Liu, Yaochu Jin, and Feng Zheng. 2022. Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcore. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_2_52_1","volume-title":"SLSG: Industrial Image Anomaly Detection by Learning Better Feature Embeddings and One-Class Classification. arXiv preprint arXiv:2305.00398(2023).","author":"Yang Minghui","year":"2023","unstructured":"Minghui Yang, Jing Liu, Zhiwei Yang, and Zhaoyang Wu. 2023. SLSG: Industrial Image Anomaly Detection by Learning Better Feature Embeddings and One-Class Classification. arXiv preprint arXiv:2305.00398(2023)."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01864"},{"key":"e_1_3_2_2_56_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Yuksekgonul Mert","year":"2022","unstructured":"Mert Yuksekgonul, Federico Bianchi, Pratyusha Kalluri, Dan Jurafsky, and James Zou. 2022. When and why vision-language models behave like bags-of-words, and what to do about it?. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_2_57_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 8330-8339","author":"Vitjan","unstructured":"Vitjan Zavrtanik et al., 2021. Draem-a discriminatively trained reconstruction embedding for surface anomaly detection. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 8330-8339."},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01460"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_23"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3737032","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T18:00:55Z","timestamp":1777572055000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3737032"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":62,"alternative-id":["10.1145\/3711896.3737032","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3737032","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}