{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T19:01:53Z","timestamp":1776452513941,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":68,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the National Natural Science Foundation of China (NSFC) National Science Fund for Distinguished Young Scholars","award":["62025301"],"award-info":[{"award-number":["62025301"]}]},{"name":"NUS Faculty Development Fund"},{"name":"the Lee Foundation in terms of Beng Chin Ooi?s Lee Kong Chian Centennial Professorship fund"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681190","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"48-57","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":21,"title":["Do LLMs Understand Visual Anomalies? Uncovering LLM's Capabilities in Zero-shot Anomaly Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9442-0318","authenticated-orcid":false,"given":"Jiaqi","family":"Zhu","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8605-076X","authenticated-orcid":false,"given":"Shaofeng","family":"Cai","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1111-7285","authenticated-orcid":false,"given":"Fang","family":"Deng","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4446-1100","authenticated-orcid":false,"given":"Beng Chin","family":"Ooi","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6742-4332","authenticated-orcid":false,"given":"Junran","family":"Wu","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00552"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00982"},{"key":"e_1_3_2_1_3_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_4_1","volume-title":"ARM-Net: Adaptive Relation Modeling Network for Structured Data. In SIGMOD '21: International Conference on Management of Data","author":"Cai Shaofeng","year":"2021","unstructured":"Shaofeng Cai, Kaiping Zheng, Gang Chen, H. V. Jagadish, Beng Chin Ooi, and Meihui Zhang. 2021. ARM-Net: Adaptive Relation Modeling Network for Structured Data. In SIGMOD '21: International Conference on Management of Data, Virtual Event, China, June 20--25, 2021, Guoliang Li, Zhanhuai Li, Stratos Idreos, and Divesh Srivastava (Eds.). ACM, 207--220."},{"key":"e_1_3_2_1_5_1","volume-title":"Segment Any Anomaly without Training via Hybrid Prompt Regularization. arXiv preprint arXiv:2305.10724","author":"Cao Yunkang","year":"2023","unstructured":"Yunkang Cao, Xiaohao Xu, Chen Sun, Yuqi Cheng, Zongwei Du, Liang Gao, and Weiming Shen. 2023. Segment Any Anomaly without Training via Hybrid Prompt Regularization. arXiv preprint arXiv:2305.10724 (2023)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00045"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611876"},{"key":"e_1_3_2_1_8_1","volume-title":"International conference on machine learning. PMLR, 1597--1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597--1607."},{"key":"e_1_3_2_1_9_1","volume-title":"1st Place on Zero-shot AD and 4th Place on Few-shot AD. arXiv preprint arXiv:2305.17382","author":"Chen Xuhai","year":"2023","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_1_10_1","volume-title":"think, confirm: Interactive prompting between vision and language models for knowledge-based visual reasoning. arXiv preprint arXiv:2301.05226","author":"Chen Zhenfang","year":"2023","unstructured":"Zhenfang Chen, Qinhong Zhou, Yikang Shen, Yining Hong, Hao Zhang, and Chuang Gan. 2023. See, think, confirm: Interactive prompting between vision and language models for knowledge-based visual reasoning. arXiv preprint arXiv:2301.05226 (2023)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00265"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68799-1_35"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00951"},{"key":"e_1_3_2_1_14_1","volume-title":"AnoVL: Adapting Vision-Language Models for Unified Zero-shot Anomaly Localization. arXiv preprint arXiv:2308.15939","author":"Deng Hanqiu","year":"2023","unstructured":"Hanqiu Deng, Zhaoxiang Zhang, Jinan Bao, and Xingyu Li. 2023. AnoVL: Adapting Vision-Language Models for Unified Zero-shot Anomaly Localization. arXiv preprint arXiv:2308.15939 (2023)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00475"},{"key":"e_1_3_2_1_16_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 1705--1714","author":"Gong Dong","unstructured":"Dong Gong, Lingqiao Liu, Vuong Le, Budhaditya Saha, Moussa Reda Mansour, Svetha Venkatesh, and Anton van den Hengel. 2019. Memorizing normality to detect anomaly: Memory-augmented deep autoencoder for unsupervised anomaly detection. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 1705--1714."},{"key":"e_1_3_2_1_18_1","volume-title":"AnomalyGPT: Detecting Industrial Anomalies using Large Vision-Language Models. arXiv preprint arXiv:2308.15366","author":"Gu Zhaopeng","year":"2023","unstructured":"Zhaopeng Gu, Bingke Zhu, Guibo Zhu, Yingying Chen, Ming Tang, and Jinqiao Wang. 2023. AnomalyGPT: Detecting Industrial Anomalies using Large Vision-Language Models. arXiv preprint arXiv:2308.15366 (2023)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","unstructured":"Gabriel Ilharco Mitchell Wortsman Ross Wightman Cade Gordon Nicholas Carlini Rohan Taori Achal Dave Vaishaal Shankar Hongseok Namkoong John Miller Hannaneh Hajishirzi Ali Farhadi and Ludwig Schmidt. 2021. OpenCLIP. https:\/\/doi.org\/10.5281\/zenodo.5143773 If you use this software please cite it as below..","DOI":"10.5281\/zenodo.5143773"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01878"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588918"},{"key":"e_1_3_2_1_22_1","unstructured":"Michael I Jordan et al. 1995. Why the logistic function? A tutorial discussion on probabilities and neural networks."},{"key":"e_1_3_2_1_23_1","volume-title":"Multi-Modal Classifiers for Open-Vocabulary Object Detection. arXiv preprint arXiv:2306.05493","author":"Kaul Prannay","year":"2023","unstructured":"Prannay Kaul, Weidi Xie, and Andrew Zisserman. 2023. Multi-Modal Classifiers for Open-Vocabulary Object Detection. arXiv preprint arXiv:2306.05493 (2023)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_26_1","volume-title":"Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa.","author":"Kojima Takeshi","year":"2022","unstructured":"Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. Advances in neural information processing systems, Vol. 35 (2022), 22199--22213."},{"key":"e_1_3_2_1_27_1","volume-title":"Seminars in Musculoskeletal Radiology","author":"Lee A","unstructured":"A Lee, J Wu, C Liu, YJ Lee, JH Tan, J Huang, N Kumar, BC Ooi, and J Hallinan. 2024. Deep Learning Model for Automated Detection and Classification of Degenerative Cord Signal Abnormality, Spinal Canal and Neural Foraminal Stenosis on Cervical Spine Magnetic Resonance Imaging. In Seminars in Musculoskeletal Radiology, Vol. 28. Thieme Medical Publishers, Inc., A132."},{"key":"e_1_3_2_1_28_1","volume-title":"The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691","author":"Lester Brian","year":"2021","unstructured":"Brian Lester, Rami Al-Rfou, and Noah Constant. 2021. The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691 (2021)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00954"},{"key":"e_1_3_2_1_30_1","volume-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)."},{"key":"e_1_3_2_1_31_1","volume-title":"MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images. arXiv preprint arXiv:2401.16753","author":"Li Xurui","year":"2024","unstructured":"Xurui Li, Ziming Huang, Feng Xue, and Yu Zhou. 2024. MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images. arXiv preprint arXiv:2401.16753 (2024)."},{"key":"e_1_3_2_1_32_1","volume-title":"Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190","author":"Li Xiang Lisa","year":"2021","unstructured":"Xiang Lisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190 (2021)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2916683"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V35I10.17067"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588936"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3130074"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3027724"},{"key":"e_1_3_2_1_38_1","volume-title":"Visual classification via description from large language models. arXiv preprint arXiv:2210.07183","author":"Menon Sachit","year":"2022","unstructured":"Sachit Menon and Carl Vondrick. 2022. Visual classification via description from large language models. arXiv preprint arXiv:2210.07183 (2022)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2807410"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01438"},{"key":"e_1_3_2_1_41_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_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01321"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01392"},{"key":"e_1_3_2_1_44_1","volume-title":"International conference on machine learning. PMLR, 4393--4402","author":"Ruff Lukas","year":"2018","unstructured":"Lukas Ruff, Robert Vandermeulen, Nico Goernitz, Lucas Deecke, Shoaib Ahmed Siddiqui, Alexander Binder, Emmanuel M\u00fcller, and Marius Kloft. 2018. Deep one-class classification. In International conference on machine learning. PMLR, 4393--4402."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995720"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01466"},{"key":"e_1_3_2_1_47_1","volume-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114","author":"Schuhmann Christoph","year":"2021","unstructured":"Christoph Schuhmann, Richard Vencu, Romain Beaumont, Robert Kaczmarczyk, Clayton Mullis, Aarush Katta, Theo Coombes, Jenia Jitsev, and Aran Komatsuzaki. 2021. Laion-400m: Open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)."},{"key":"e_1_3_2_1_48_1","volume-title":"Synthetic prompting: Generating chain-of-thought demonstrations for large language models. arXiv preprint arXiv:2302.00618","author":"Shao Zhihong","year":"2023","unstructured":"Zhihong Shao, Yeyun Gong, Yelong Shen, Minlie Huang, Nan Duan, and Weizhu Chen. 2023. Synthetic prompting: Generating chain-of-thought demonstrations for large language models. arXiv preprint arXiv:2302.00618 (2023)."},{"key":"e_1_3_2_1_49_1","volume-title":"Pandagpt: One model to instruction-follow them all. arXiv preprint arXiv:2305.16355","author":"Su Yixuan","year":"2023","unstructured":"Yixuan Su, Tian Lan, Huayang Li, Jialu Xu, Yan Wang, and Deng Cai. 2023. Pandagpt: One model to instruction-follow them all. arXiv preprint arXiv:2305.16355 (2023)."},{"key":"e_1_3_2_1_50_1","volume-title":"Random Word Data Augmentation with CLIP for Zero-Shot Anomaly Detection. arXiv preprint arXiv:2308.11119","author":"Tamura Masato","year":"2023","unstructured":"Masato Tamura. 2023. Random Word Data Augmentation with CLIP for Zero-Shot Anomaly Detection. arXiv preprint arXiv:2308.11119 (2023)."},{"key":"e_1_3_2_1_51_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_52_1","volume-title":"Proceedings of the Asian conference on computer vision.","author":"Yi Jihun","year":"2020","unstructured":"Jihun Yi and Sungroh Yoon. 2020. Patch svdd: Patch-level svdd for anomaly detection and segmentation. In Proceedings of the Asian conference on computer vision."},{"key":"e_1_3_2_1_53_1","first-page":"4571","article-title":"A unified model for multi-class anomaly detection","volume":"35","author":"You Zhiyuan","year":"2022","unstructured":"Zhiyuan You, Lei Cui, Yujun Shen, Kai Yang, Xin Lu, Yu Zheng, and Xinyi Le. 2022. A unified model for multi-class anomaly detection. Advances in Neural Information Processing Systems, Vol. 35 (2022), 4571--4584.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00290"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00822"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01460"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00381"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3093883"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859596"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"e_1_3_2_1_61_1","volume-title":"Proceedings, Part XX 16","author":"Zhou Kang","year":"2020","unstructured":"Kang Zhou, Yuting Xiao, Jianlong Yang, Jun Cheng, Wen Liu, Weixin Luo, Zaiwang Gu, Jiang Liu, and Shenghua Gao. 2020. Encoding structure-texture relation with p-net for anomaly detection in retinal images. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XX 16. Springer, 360--377."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"e_1_3_2_1_63_1","volume-title":"Anomalyclip: Object-agnostic prompt learning for zero-shot anomaly detection. arXiv preprint arXiv:2310.18961","author":"Zhou Qihang","year":"2023","unstructured":"Qihang Zhou, Guansong Pang, Yu Tian, Shibo He, and Jiming Chen. 2023. Anomalyclip: Object-agnostic prompt learning for zero-shot anomaly detection. arXiv preprint arXiv:2310.18961 (2023)."},{"key":"e_1_3_2_1_64_1","volume-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592","author":"Zhu Deyao","year":"2023","unstructured":"Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.14778\/3636218.3636233"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108897"},{"key":"e_1_3_2_1_67_1","volume-title":"Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts. arXiv preprint arXiv:2403.06495","author":"Zhu Jiawen","year":"2024","unstructured":"Jiawen Zhu and Guansong Pang. 2024. Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts. arXiv preprint arXiv:2403.06495 (2024)."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_23"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681190","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681190","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:02Z","timestamp":1750295882000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681190"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":68,"alternative-id":["10.1145\/3664647.3681190","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681190","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}