{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T03:51:18Z","timestamp":1783828278103,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276280"],"award-info":[{"award-number":["62276280"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangzhou Science and Technology Planning Project","award":["2024A04J9967"],"award-info":[{"award-number":["2024A04J9967"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755635","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:27:39Z","timestamp":1761377259000},"page":"4846-4855","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["AF-CLIP: Zero-Shot Anomaly Detection via Anomaly-Focused CLIP Adaptation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9876-9863","authenticated-orcid":false,"given":"Qingqing","family":"Fang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3258-8886","authenticated-orcid":false,"given":"Wenxi","family":"Lv","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5903-2504","authenticated-orcid":false,"given":"Qinliang","family":"Su","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China and Guangdong Key Laboratory of Big Data Analysis and Processing, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"MVTec AD - A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection. In IEEE Conference on Computer Vision and Pattern Recognition. Computer Vision Foundation \/ IEEE, 9592-9600","author":"Bergmann Paul","year":"2019","unstructured":"Paul Bergmann, Michael Fauser, David Sattlegger, and Carsten Steger. 2019. MVTec AD - A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection. In IEEE Conference on Computer Vision and Pattern Recognition. Computer Vision Foundation \/ IEEE, 9592-9600."},{"key":"e_1_3_2_1_2_1","volume-title":"WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians. Computerized medical imaging and graphics","author":"Bernal Jorge","year":"2015","unstructured":"Jorge Bernal, F Javier S\u00e1nchez, Gloria Fern\u00e1ndez-Esparrach, Debora Gil, Cristina Rodr\u00edguez, and Fernando Vilari no. 2015. WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians. Computerized medical imaging and graphics, Vol. 43 (2015), 99-111."},{"key":"e_1_3_2_1_3_1","volume-title":"European Conference on Computer Vision. Springer, 55-72","author":"Cao Yunkang","year":"2024","unstructured":"Yunkang Cao, Jiangning Zhang, Luca Frittoli, Yuqi Cheng, Weiming Shen, and Giacomo Boracchi. 2024. Adaclip: Adapting clip with hybrid learnable prompts for zero-shot anomaly detection. In European Conference on Computer Vision. Springer, 55-72."},{"key":"e_1_3_2_1_4_1","volume-title":"A zero-\/fewshot 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","author":"Chen Xuhai","year":"2023","unstructured":"Xuhai Chen, Yue Han, and Jiangning Zhang. 2023. A zero-\/fewshot 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, Vol. 2, 4 (2023)."},{"key":"e_1_3_2_1_5_1","unstructured":"Noel Codella Veronica Rotemberg Philipp Tschandl M Emre Celebi Stephen Dusza David Gutman Brian Helba Aadi Kalloo Konstantinos Liopyris Michael Marchetti et al. 2019. Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (isic). arXiv preprint arXiv:1902.03368 (2019)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681376"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00951"},{"key":"e_1_3_2_1_8_1","volume-title":"International Conference on Learning Representations.","author":"Dosovitskiy Alexey","year":"2020","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. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i16.33816"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01603"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27963"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00188"},{"key":"e_1_3_2_1_13_1","volume-title":"Br35h: Brain tumor detection","year":"2020","unstructured":"Hamada. 2020. Br35h: Brain tumor detection 2020. (2020). https:\/\/www.kaggle.com\/datasets\/ahmedhamada0\/brain-tumor-detection, 2020"},{"key":"e_1_3_2_1_14_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations","volume":"1","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al., 2022. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations, Vol. 1. 3."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_18"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00205"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01878"},{"key":"e_1_3_2_1_18_1","first-page":"451","volume-title":"MMM 2020, Daejeon, South Korea, January 5-8, 2020, proceedings, part II 26","author":"Jha Debesh","year":"2020","unstructured":"Debesh Jha, Pia H Smedsrud, Michael A Riegler, P\u00e5l Halvorsen, Thomas De Lange, Dag Johansen, and H\u00e5vard D Johansen. 2020. Kvasir-seg: A segmented polyp dataset. In MultiMedia modeling: 26th international conference, MMM 2020, Daejeon, South Korea, January 5-8, 2020, proceedings, part II 26. Springer, 451-462."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00954"},{"key":"e_1_3_2_1_22_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023a. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730-19742."},{"key":"e_1_3_2_1_23_1","volume-title":"International conference on machine learning. PMLR, 12888-12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning. PMLR, 12888-12900."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01594"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Li Xiang Lisa","unstructured":"Xiang Lisa Li and Percy Liang. 2021. Prefix-Tuning: Optimizing Continuous Prompts for Generation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Association for Computational Linguistics."},{"key":"e_1_3_2_1_26_1","volume-title":"Clip surgery for better explainability with enhancement in open-vocabulary tasks. arXiv preprint arXiv:2304.05653","author":"Li Yi","year":"2023","unstructured":"Yi Li, Hualiang Wang, Yiqun Duan, and Xiaomeng Li. 2023b. Clip surgery for better explainability with enhancement in open-vocabulary tasks. arXiv preprint arXiv:2304.05653 (2023)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01954"},{"key":"e_1_3_2_1_29_1","volume-title":"The Thirteenth International Conference on Learning Representations.","author":"Lv Wenxi","year":"2025","unstructured":"Wenxi Lv, Qinliang Su, and Wenchao Xu. 2025. One-for-All Few-Shot Anomaly Detection via Instance-Induced Prompt Learning. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Ma Wenxin","unstructured":"Wenxin Ma, Xu Zhang, Qingsong Yao, Fenghe Tang, Chenxu Wu, Yingtai Li, Rui Yan, Zihang Jiang, and S. Kevin Zhou. 2025. AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISIE45552.2021.9576231"},{"key":"e_1_3_2_1_32_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_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25309"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01392"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00195"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01466"},{"key":"e_1_3_2_1_37_1","volume-title":"Automated polyp detection in colonoscopy videos using shape and context information","author":"Tajbakhsh Nima","year":"2015","unstructured":"Nima Tajbakhsh, Suryakanth R Gurudu, and Jianming Liang. 2015. Automated polyp detection in colonoscopy videos using shape and context information. IEEE transactions on medical imaging, Vol. 35, 2 (2015), 630-644."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00398"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02348"},{"key":"e_1_3_2_1_40_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems","author":"Vaswani A","year":"2017","unstructured":"A Vaswani. 2017. Attention is all you need. Advances in Neural Information Processing Systems (2017)."},{"key":"e_1_3_2_1_41_1","volume-title":"DAGM symposium in","volume":"6","author":"Wieler Matthias","year":"2007","unstructured":"Matthias Wieler and Tobias Hahn. 2007. Weakly supervised learning for industrial optical inspection. In DAGM symposium in, Vol. 6. 11."},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of the Asian conference on computer vision. 375-390","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. 375-390."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00822"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107706"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/330"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00381"},{"key":"e_1_3_2_1_47_1","volume-title":"AE-FLOW: Autoencoders with Normalizing Flows for Medical Images Anomaly Detection. In The Eleventh International Conference on Learning Representations.","author":"Zhao Yuzhong","year":"2023","unstructured":"Yuzhong Zhao, Qiaoqiao Ding, and Xiaoqun Zhang. 2023. AE-FLOW: Autoencoders with Normalizing Flows for Medical Images Anomaly Detection. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_1_49_1","volume-title":"AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection. In The Twelfth International Conference on Learning Representations.","author":"Zhou Qihang","year":"2024","unstructured":"Qihang Zhou, Guansong Pang, Yu Tian, Shibo He, and Jiming Chen. 2024. AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01688"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_23"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755635","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:00:16Z","timestamp":1765342816000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755635"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":51,"alternative-id":["10.1145\/3746027.3755635","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755635","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}