{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T10:17:09Z","timestamp":1789726629304,"version":"4.0.1"},"publisher-location":"New York, NY, USA","reference-count":71,"publisher":"ACM","funder":[{"name":"the Key Research and Development Program of Heilongjiang Province of China","award":["2022ZX01A21"],"award-info":[{"award-number":["2022ZX01A21"]}]},{"name":"the State Key Laboratory of Massive Personalized Customization System and Technology, COSMOPlat Institute of Industrial Intelligence (Qingdao) Co. Ltd., located in Qingdao 266100, China."}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755725","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:55:00Z","timestamp":1761375300000},"page":"5030-5039","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["SAGE: A Visual Language Model for Anomaly Detection via Fact Enhancement and Entropy-aware Alignment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9155-1797","authenticated-orcid":false,"given":"Guoxin","family":"Zang","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5885-0794","authenticated-orcid":false,"given":"Xue","family":"Li","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2270-3378","authenticated-orcid":false,"given":"Donglin","family":"Di","sequence":"additional","affiliation":[{"name":"DZ Matrix, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2079-1252","authenticated-orcid":false,"given":"Lanshun","family":"Nie","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5973-9542","authenticated-orcid":false,"given":"Dechen","family":"Zhan","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1283-1672","authenticated-orcid":false,"given":"Yang","family":"Song","sequence":"additional","affiliation":[{"name":"University of New South Wales, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9472-7152","authenticated-orcid":false,"given":"Lei","family":"Fan","sequence":"additional","affiliation":[{"name":"University of New South Wales, Sydney, Australia and DZ Matrix, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Jean-Baptiste Alayrac Jeff Donahue Pauline Luc Antoine Miech Iain Barr Yana Hasson Karel Lenc Arthur Mensch Katherine Millican Malcolm Reynolds et al. 2022. Flamingo: a visual language model for few-shot learning. Advances in neural information processing systems Vol. 35 (2022) 23716-23736."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00586"},{"key":"e_1_3_2_1_4_1","volume-title":"Qwen-VL: A Frontier Large Vision-Language Model with Versatile Abilities. arXiv preprint arXiv:2308.12966","author":"Bai Jinze","year":"2023","unstructured":"Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023. Qwen-VL: A Frontier Large Vision-Language Model with Versatile Abilities. arXiv preprint arXiv:2308.12966 (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00982"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00424"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.2307\/2334029"},{"key":"e_1_3_2_1_8_1","volume-title":"Anomaly Detection by Adapting a pre-trained Vision Language Model. arXiv preprint arXiv:2403.09493","author":"Cai Yuxuan","year":"2024","unstructured":"Yuxuan Cai, Xinwei He, Dingkang Liang, Ao Tong, and Xiang Bai. 2024. Anomaly Detection by Adapting a pre-trained Vision Language Model. arXiv preprint arXiv:2403.09493 (2024)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 24185-24198","author":"Chen Zhe","year":"2024","unstructured":"Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, et al., 2024. Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 24185-24198."},{"key":"e_1_3_2_1_11_1","volume-title":"Xing","author":"Chiang Wei-Lin","year":"2023","unstructured":"Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E. Gonzalez, Ion Stoica, and Eric P. Xing. 2023. Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality."},{"key":"e_1_3_2_1_12_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_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"e_1_3_2_1_14_1","volume-title":"Sub-image anomaly detection with deep pyramid correspondences. arXiv preprint arXiv:2005.02357","author":"Cohen Niv","year":"2020","unstructured":"Niv Cohen and Yedid Hoshen. 2020. Sub-image anomaly detection with deep pyramid correspondences. arXiv preprint arXiv:2005.02357 (2020)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68799-1_35"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Matt Deitke Christopher Clark Sangho Lee Rohun Tripathi Yue Yang Jae Sung Park Mohammadreza Salehi Niklas Muennighoff Kyle Lo Luca Soldaini Jiasen Lu Taira Anderson Erin Bransom Kiana Ehsani Huong Ngo YenSung Chen Ajay Patel Mark Yatskar Chris Callison-Burch Andrew Head Rose Hendrix Favyen Bastani Eli VanderBilt Nathan Lambert Yvonne Chou Arnavi Chheda Jenna Sparks Sam Skjonsberg Michael Schmitz Aaron Sarnat Byron Bischoff Pete Walsh Chris Newell Piper Wolters Tanmay Gupta Kuo-Hao Zeng Jon Borchardt Dirk Groeneveld Jen Dumas Crystal Nam Sophie Lebrecht Caitlin Wittlif Carissa Schoenick Oscar Michel Ranjay Krishna Luca Weihs Noah A. Smith Hannaneh Hajishirzi Ross Girshick Ali Farhadi and Aniruddha Kembhavi. 2024. Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models. arXiv preprint arXiv:2409.17146 (2024).","DOI":"10.1109\/CVPR52734.2025.00018"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00951"},{"key":"e_1_3_2_1_18_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_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2897122"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230329"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446994"},{"key":"e_1_3_2_1_22_1","volume-title":"GrainBrain: Multiview Identification and Stratification of Defective Grain Kernels","author":"Fan Lei","year":"2025","unstructured":"Lei Fan, Dongdong Fan, Yiwen Ding, Yong Wu, Donglin Di, Maurice Pagnucco, and Yang Song. 2025. GrainBrain: Multiview Identification and Stratification of Defective Grain Kernels. IEEE Transactions on Industrial Informatics (2025)."},{"key":"e_1_3_2_1_23_1","volume-title":"MANTA: A Large-Scale Multi-View and Visual-Text Anomaly Detection Dataset for Tiny Objects. arXiv preprint arXiv:2412.04867","author":"Fan Lei","year":"2024","unstructured":"Lei Fan, Dongdong Fan, Zhiguang Hu, Yiwen Ding, Donglin Di, Kai Yi, Maurice Pagnucco, and Yang Song. 2024b. MANTA: A Large-Scale Multi-View and Visual-Text Anomaly Detection Dataset for Tiny Objects. arXiv preprint arXiv:2412.04867 (2024)."},{"key":"e_1_3_2_1_24_1","volume-title":"Salvaging the Overlooked: Leveraging Class-Aware Contrastive Learning for Multi-Class Anomaly Detection. arXiv preprint arXiv:2412.04769","author":"Fan Lei","year":"2024","unstructured":"Lei Fan, Junjie Huang, Donglin Di, Anyang Su, Tianyou Song, Maurice Pagnucco, and Yang Song. 2024c. Salvaging the Overlooked: Leveraging Class-Aware Contrastive Learning for Multi-Class Anomaly Detection. arXiv preprint arXiv:2412.04769 (2024)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3378771"},{"key":"e_1_3_2_1_26_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_27_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_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01591"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_30_1","unstructured":"Aaron Hurst Adam Lerer Adam P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et al. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)."},{"key":"e_1_3_2_1_31_1","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. If you use this software please cite it as below.."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01878"},{"key":"e_1_3_2_1_33_1","volume-title":"2021 13th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT). 66-71","author":"Jezek Stepan","unstructured":"Stepan Jezek, Martin Jonak, Radim Burget, Pavel Dvorak, and Milos Skotak. [n.d.]. Deep learning-based defect detection of metal parts: evaluating current methods in complex conditions. In 2021 13th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT). 66-71."},{"key":"e_1_3_2_1_34_1","volume-title":"Mmad: The first-ever comprehensive benchmark for multimodal large language models in industrial anomaly detection. arXiv preprint arXiv:2410.09453","author":"Jiang Xi","year":"2024","unstructured":"Xi Jiang, Jian Li, Hanqiu Deng, Yong Liu, Bin-Bin Gao, Yifeng Zhou, Jialin Li, Chengjie Wang, and Feng Zheng. 2024. Mmad: The first-ever comprehensive benchmark for multimodal large language models in industrial anomaly detection. arXiv preprint arXiv:2410.09453 (2024)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00954"},{"key":"e_1_3_2_1_37_1","volume-title":"International conference on machine learning. PMLR","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. In International conference on machine learning. PMLR, 19730-19742."},{"key":"e_1_3_2_1_38_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_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02096"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2025.3545987"},{"key":"e_1_3_2_1_41_1","unstructured":"Haotian Liu Chunyuan Li Yuheng Li Bo Li Yuanhan Zhang Sheng Shen and Yong Jae Lee. 2024. LLaVA-NeXT: Improved reasoning OCR and world knowledge."},{"key":"e_1_3_2_1_42_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2023), 34892-34916."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISIE45552.2021.9576231"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596772"},{"key":"e_1_3_2_1_45_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_46_1","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems.","author":"Rafailov Rafael","year":"2023","unstructured":"Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2023. Direct Preference Optimization: Your Language Model is Secretly a Reward Model. In Thirty-seventh Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_47_1","volume-title":"Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084","author":"Reimers Nils","year":"2019","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084 (2019)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00283"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01392"},{"key":"e_1_3_2_1_50_1","volume-title":"Support vector method for novelty detection. Advances in neural information processing systems","author":"Sch\u00f6lkopf Bernhard","year":"1999","unstructured":"Bernhard Sch\u00f6lkopf, Robert C Williamson, Alex Smola, John Shawe-Taylor, and John Platt. 1999. Support vector method for novelty detection. Advances in neural information processing systems, Vol. 12 (1999)."},{"key":"e_1_3_2_1_51_1","volume-title":"Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track.","author":"Schuhmann Christoph","year":"2022","unstructured":"Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade W Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, Patrick Schramowski, Srivatsa R Kundurthy, Katherine Crowson, Ludwig Schmidt, Robert Kaczmarczyk, and Jenia Jitsev. 2022. LAION-5B: An open large-scale dataset for training next generation image-text models. In Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_9"},{"key":"e_1_3_2_1_53_1","volume-title":"International Conference on Machine Learning. PMLR, 9880-9890","author":"Su Xiu","year":"2021","unstructured":"Xiu Su, Shan You, Mingkai Zheng, Fei Wang, Chen Qian, Changshui Zhang, and Chang Xu. 2021. K-shot nas: Learnable weight-sharing for nas with k-shot supernets. In International Conference on Machine Learning. PMLR, 9880-9890."},{"key":"e_1_3_2_1_54_1","volume-title":"Support vector data description. Machine learning","author":"Tax David MJ","year":"2004","unstructured":"David MJ Tax and Robert PW Duin. 2004. Support vector data description. Machine learning, Vol. 54 (2004), 45-66."},{"key":"e_1_3_2_1_55_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_56_1","volume-title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution. arXiv preprint arXiv:2409.12191","author":"Wang Peng","year":"2024","unstructured":"Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Yang Fan, Kai Dang, Mengfei Du, Xuancheng Ren, Rui Men, Dayiheng Liu, Chang Zhou, Jingren Zhou, and Junyang Lin. 2024. Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution. arXiv preprint arXiv:2409.12191 (2024)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00776"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28423"},{"key":"e_1_3_2_1_59_1","unstructured":"Zhiyu Wu Xiaokang Chen Zizheng Pan Xingchao Liu Wen Liu Damai Dai Huazuo Gao Yiyang Ma Chengyue Wu Bingxuan Wang Zhenda Xie Yu Wu Kai Hu Jiawei Wang Yaofeng Sun Yukun Li Yishi Piao Kang Guan Aixin Liu Xin Xie Yuxiang You Kai Dong Xingkai Yu Haowei Zhang Liang Zhao Yisong Wang and Chong Ruan. 2024a. DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding."},{"key":"e_1_3_2_1_60_1","volume-title":"Forty-first International Conference on Machine Learning.","author":"Wu Zhongze","year":"2024","unstructured":"Zhongze Wu, Hongyan Xu, Yitian Long, Shan You, Xiu Su, Jun Long, Yueyi Luo, and Chang Xu. 2024b. Detecting Any instruction-to-answer interaction relationship: Universal Instruction-to-Answer Navigator for Med-VQA. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_2_1_61_1","volume-title":"Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models. arXiv preprint arXiv:2502.07601","author":"Xu Jiacong","year":"2025","unstructured":"Jiacong Xu, Shao-Yuan Lo, Bardia Safaei, Vishal M Patel, and Isht Dwivedi. 2025. Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models. arXiv preprint arXiv:2502.07601 (2025)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3273681"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3563775"},{"key":"e_1_3_2_1_64_1","volume-title":"DSDNet: Raw Domain Demoieing via Dual Color-Space Synergy. arXiv preprint arXiv:2504.15756","author":"Yang Qirui","year":"2025","unstructured":"Qirui Yang, Fangpu Zhang, Yeying Jin, Qihua Cheng, Pengtao Jiang, Huanjing Yue, and Jingyu Yang. 2025b. DSDNet: Raw Domain Demoieing via Dual Color-Space Synergy. arXiv preprint arXiv:2504.15756 (2025)."},{"key":"e_1_3_2_1_65_1","volume-title":"European Conference on Computer Vision. Springer, 304-322","author":"Yang Yuchen","year":"2024","unstructured":"Yuchen Yang, Kwonjoon Lee, Behzad Dariush, Yinzhi Cao, and Shao-Yuan Lo. 2024. Follow the rules: reasoning for video anomaly detection with large language models. In European Conference on Computer Vision. Springer, 304-322."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2024.01.004"},{"key":"e_1_3_2_1_67_1","volume-title":"SIFT: Grounding LLM Reasoning in Contexts via Stickers.","author":"Zeng Zihao","year":"2025","unstructured":"Zihao Zeng, Xuyao Huang, Boxiu Li, and Zhijie Deng. 2025. SIFT: Grounding LLM Reasoning in Contexts via Stickers."},{"key":"e_1_3_2_1_68_1","volume-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605","author":"Zhang Hao","year":"2022","unstructured":"Hao Zhang, Feng Li, Shilong Liu, Lei Zhang, Hang Su, Jun Zhu, Lionel M Ni, and Heung-Yeung Shum. 2022. Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022)."},{"key":"e_1_3_2_1_69_1","unstructured":"Lianmin Zheng Wei-Lin Chiang Ying Sheng Siyuan Zhuang Zhanghao Wu Yonghao Zhuang Zi Lin Zhuohan Li Dacheng Li Eric. P Xing Hao Zhang Joseph E. Gonzalez and Ion Stoica. 2023. Judging LLM-as-a-judge with MT-Bench and Chatbot Arena."},{"key":"e_1_3_2_1_70_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":"2023","unstructured":"Qihang Zhou, Guansong Pang, Yu Tian, Shibo He, and Jiming Chen. 2023. AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_71_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\/3746027.3755725","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:00:48Z","timestamp":1765339248000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755725"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":71,"alternative-id":["10.1145\/3746027.3755725","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755725","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"}}]}}