{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T20:25:48Z","timestamp":1773779148676,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":53,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681376","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"1761-1770","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["SimCLIP: Refining Image-Text Alignment with Simple Prompts for Zero-\/Few-shot Anomaly Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2806-6542","authenticated-orcid":false,"given":"Chenghao","family":"Deng","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7106-2207","authenticated-orcid":false,"given":"Haote","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2296-4909","authenticated-orcid":false,"given":"Xiaolu","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4915-5738","authenticated-orcid":false,"given":"Haodi","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7190-2429","authenticated-orcid":false,"given":"Xiaotong","family":"Tu","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2288-5287","authenticated-orcid":false,"given":"Xinghao","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University & Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3913-9400","authenticated-orcid":false,"given":"Yue","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}]}],"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\/ICCV51070.2023.00130"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00071"},{"key":"e_1_3_2_1_5_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_6_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_7_1","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery Aakanksha","year":"2023","unstructured":"Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. 2023. Palm: Scaling language modeling with pathways. Journal of Machine Learning Research, Vol. 24, 240 (2023), 1--113.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_8_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_9_1","volume-title":"Open-vocabulary panoptic segmentation with maskclip. arXiv preprint arXiv:2208.08984","author":"Ding Zheng","year":"2022","unstructured":"Zheng Ding, Jieke Wang, and Zhuowen Tu. 2022. Open-vocabulary panoptic segmentation with maskclip. arXiv preprint arXiv:2208.08984 (2022)."},{"key":"e_1_3_2_1_10_1","volume-title":"Making pre-trained language models better few-shot learners. arXiv preprint arXiv:2012.15723","author":"Gao Tianyu","year":"2020","unstructured":"Tianyu Gao, Adam Fisch, and Danqi Chen. 2020. Making pre-trained language models better few-shot learners. arXiv preprint arXiv:2012.15723 (2020)."},{"key":"e_1_3_2_1_11_1","volume-title":"Domain adaptation via prompt learning","author":"Ge Chunjiang","year":"2023","unstructured":"Chunjiang Ge, Rui Huang, Mixue Xie, Zihang Lai, Shiji Song, Shuang Li, and Gao Huang. 2023. Domain adaptation via prompt learning. IEEE Transactions on Neural Networks and Learning Systems (2023)."},{"key":"e_1_3_2_1_12_1","volume-title":"Open-vocabulary object detection via vision and language knowledge distillation. arXiv preprint arXiv:2104.13921","author":"Gu Xiuye","year":"2021","unstructured":"Xiuye Gu, Tsung-Yi Lin, Weicheng Kuo, and Yin Cui. 2021. Open-vocabulary object detection via vision and language knowledge distillation. arXiv preprint arXiv:2104.13921 (2021)."},{"key":"e_1_3_2_1_13_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_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_15_1","volume-title":"International Conference on Machine Learning. PMLR, 2790--2799","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for NLP. In International Conference on Machine Learning. PMLR, 2790--2799."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_18"},{"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","volume-title":"International conference on machine learning. PMLR, 4904--4916","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling up visual and vision-language representation learning with noisy text supervision. In International conference on machine learning. PMLR, 4904--4916."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"e_1_3_2_1_21_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_22_1","volume-title":"Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461","author":"Lewis Mike","year":"2019","unstructured":"Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, and Luke Zettlemoyer. 2019. Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461 (2019)."},{"key":"e_1_3_2_1_23_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_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00113"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_2_1_27_1","volume-title":"Cma-clip: Cross-modality attention clip for image-text classification. arXiv preprint arXiv:2112.03562","author":"Liu Huidong","year":"2021","unstructured":"Huidong Liu, Shaoyuan Xu, Jinmiao Fu, Yang Liu, Ning Xie, Chien-Chih Wang, Bryan Wang, and Yi Sun. 2021. Cma-clip: Cross-modality attention clip for image-text classification. arXiv preprint arXiv:2112.03562 (2021)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"e_1_3_2_1_29_1","volume-title":"V-net: Fully convolutional neural networks for volumetric medical image segmentation. In 2016 fourth international conference on 3D vision (3DV). Ieee, 565--571.","author":"Milletari Fausto","year":"2016","unstructured":"Fausto Milletari, Nassir Navab, and Seyed-Ahmad Ahmadi. 2016. V-net: Fully convolutional neural networks for volumetric medical image segmentation. In 2016 fourth international conference on 3D vision (3DV). Ieee, 565--571."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"e_1_3_2_1_31_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_32_1","unstructured":"Aditya Ramesh Prafulla Dhariwal Alex Nichol Casey Chu and Mark Chen. [n. d.]. Hierarchical Text-Conditional Image Generation with CLIP Latents. ( [n. d.])."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"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","volume-title":"Eric Wallace, and Sameer Singh.","author":"Shin Taylor","year":"2020","unstructured":"Taylor Shin, Yasaman Razeghi, Robert L Logan IV, Eric Wallace, and Sameer Singh. 2020. Autoprompt: Eliciting knowledge from language models with automatically generated prompts. arXiv preprint arXiv:2010.15980 (2020)."},{"key":"e_1_3_2_1_36_1","first-page":"14274","article-title":"Test-time prompt tuning for zero-shot generalization in vision-language models","volume":"35","author":"Shu Manli","year":"2022","unstructured":"Manli Shu, Weili Nie, De-An Huang, Zhiding Yu, Tom Goldstein, Anima Anandkumar, and Chaowei Xiao. 2022. Test-time prompt tuning for zero-shot generalization in vision-language models. Advances in Neural Information Processing Systems, Vol. 35 (2022), 14274--14289.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_37_1","volume-title":"Reclip: A strong zero-shot baseline for referring expression comprehension. arXiv preprint arXiv:2204.05991","author":"Subramanian Sanjay","year":"2022","unstructured":"Sanjay Subramanian, William Merrill, Trevor Darrell, Matt Gardner, Sameer Singh, and Anna Rohrbach. 2022. Reclip: A strong zero-shot baseline for referring expression comprehension. arXiv preprint arXiv:2204.05991 (2022)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Zeyi Sun Ye Fang Tong Wu Pan Zhang Yuhang Zang Shu Kong Yuanjun Xiong Dahua Lin and Jiaqi Wang. 2023. Alpha-CLIP: A CLIP Model Focusing on Wherever You Want. arxiv: 2312.03818 [cs.CV]","DOI":"10.1109\/CVPR52733.2024.01237"},{"key":"e_1_3_2_1_39_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_40_1","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume":"34","author":"Tsimpoukelli Maria","year":"2021","unstructured":"Maria Tsimpoukelli, Jacob L Menick, Serkan Cabi, SM Eslami, Oriol Vinyals, and Felix Hill. 2021. Multimodal few-shot learning with frozen language models. Advances in Neural Information Processing Systems, Vol. 34 (2021), 200--212.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_41_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research, Vol. 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00173"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"e_1_3_2_1_44_1","volume-title":"Side Adapter Network for Open-Vocabulary Semantic Segmentation. (Feb","author":"Xu Mengde","year":"2023","unstructured":"Mengde Xu, Zheng Zhang, Fangyun Wei, Han Hu, and Xiang Bai. 2023. Side Adapter Network for Open-Vocabulary Semantic Segmentation. (Feb 2023)."},{"key":"e_1_3_2_1_45_1","unstructured":"Xin Xu Tianyi Xiong Zheng Ding and Zhuowen Tu. [n. d.]. MasQCLIP for Open-Vocabulary Universal Image Segmentation. ( [n. d.])."},{"key":"e_1_3_2_1_46_1","volume-title":"Cpt: Colorful prompt tuning for pre-trained vision-language models. arXiv preprint arXiv:2109.11797","author":"Yao Yuan","year":"2021","unstructured":"Yuan Yao, Ao Zhang, Zhengyan Zhang, Zhiyuan Liu, Tat-Seng Chua, and Maosong Sun. 2021. Cpt: Colorful prompt tuning for pre-trained vision-language models. arXiv preprint arXiv:2109.11797 (2021)."},{"key":"e_1_3_2_1_47_1","volume-title":"Xi Victoria Lin, et al","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al. 2022. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)."},{"key":"e_1_3_2_1_48_1","volume-title":"Extract Free Dense Labels from CLIP. (Dec","author":"Zhou Chong","year":"2021","unstructured":"Chong Zhou, ChenChange Loy, and Bo Dai. 2021. Extract Free Dense Labels from CLIP. (Dec 2021)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_1_52_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_53_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\/3664647.3681376","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681376","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:44Z","timestamp":1750295864000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681376"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":53,"alternative-id":["10.1145\/3664647.3681376","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681376","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"}}]}}