{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T17:00:26Z","timestamp":1788973226928,"version":"build-2803163510"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","funder":[{"name":"NSFC","award":["No. 62402426, 62272411, 62441617"],"award-info":[{"award-number":["No. 62402426, 62272411, 62441617"]}]},{"name":"Key Research and Development Projects in Zhejiang Province","award":["No. 2025C01128, 2024C01106, 2025C01030, 2025C02156"],"award-info":[{"award-number":["No. 2025C01128, 2024C01106, 2025C01030, 2025C02156"]}]},{"name":"Ningbo Yongjiang Talent Introduction Programme","award":["2023A-400-G"],"award-info":[{"award-number":["2023A-400-G"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["226-2025-00057"],"award-info":[{"award-number":["226-2025-00057"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754766","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:27:39Z","timestamp":1761377259000},"page":"7317-7326","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Robust Modality-Incomplete Anomaly Detection: A Modality-Instructive Framework with Benchmark"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9028-9058","authenticated-orcid":false,"given":"Bingchen","family":"Miao","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5988-7609","authenticated-orcid":false,"given":"Wenqiao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2258-1291","authenticated-orcid":false,"given":"Juncheng","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8404-9489","authenticated-orcid":false,"given":"Wangyu","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Liverpool, Liverpool, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7356-9711","authenticated-orcid":false,"given":"Siliang","family":"Tang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6592-5682","authenticated-orcid":false,"given":"Zhaocheng","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9999-8979","authenticated-orcid":false,"given":"Haochen","family":"Shi","sequence":"additional","affiliation":[{"name":"Universit\u00e9 de Montr\u00e9al, Universit\u00e9 de Montr\u00e9al, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6142-9914","authenticated-orcid":false,"given":"Jun","family":"Xiao","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9017-2508","authenticated-orcid":false,"given":"Yueting","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, 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":"Kriti Aggarwal, Subhojit Som, Songhao Piao, and Furu Wei.","author":"Bao Hangbo","year":"2022","unstructured":"Hangbo Bao, Wenhui Wang, Li Dong, Qiang Liu, Owais Khan Mohammed, Kriti Aggarwal, Subhojit Som, Songhao Piao, and Furu Wei. 2022. VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts. In Advances in Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=bydKs84JEyw"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01578-9"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00424"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5220\/0010865000003124"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00264"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the Asian Conference on Computer Vision (ACCV). 3586-3602","author":"Bonfiglioli Luca","year":"2022","unstructured":"Luca Bonfiglioli, Marco Toschi, Davide Silvestri, Nicola Fioraio, and Daniele De Gregorio. 2022. The Eyecandies Dataset for Unsupervised Multimodal Anomaly Detection and Localization. In Proceedings of the Asian Conference on Computer Vision (ACCV). 3586-3602."},{"key":"e_1_3_2_1_7_1","first-page":"447","volume-title":"Shenzhen","author":"Chen Cheng","year":"2019","unstructured":"Cheng Chen, Qi Dou, Yueming Jin, Hao Chen, Jing Qin, and Pheng-Ann Heng. 2019. Robust multimodal brain tumor segmentation via feature disentanglement and gated fusion. In Medical Image Computing and Computer Assisted Intervention-MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13-17, 2019, Proceedings, Part III 22. Springer, 447-456."},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning. 6185-6194","author":"Chu Yu-Min","year":"2023","unstructured":"Yu-Min Chu, Chieh Liu, Ting-I Hsieh, Hwann-Tzong Chen, and Tyng-Luh Liu. 2023. Shape-Guided Dual-Memory Learning for 3D Anomaly Detection. In Proceedings of the 40th International Conference on Machine Learning. 6185-6194."},{"key":"e_1_3_2_1_9_1","volume-title":"Anomaly localization by modeling perceptual features. arXiv preprint arXiv:2008.05369","author":"Dehaene David","year":"2020","unstructured":"David Dehaene and Pierre Eline. 2020. Anomaly localization by modeling perceptual features. arXiv preprint arXiv:2008.05369 (2020)."},{"key":"e_1_3_2_1_10_1","first-page":"3","volume-title":"Proceedings of the 9th International Conference on Learning Representations, ICLR","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In Proceedings of the 9th International Conference on Learning Representations, ICLR 2021. 3-7."},{"key":"e_1_3_2_1_11_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_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00188"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00188"},{"key":"e_1_3_2_1_14_1","volume-title":"HyperNetworks. In 5th International Conference on Learning Representations, ICLR","author":"Ha David","year":"2017","unstructured":"David Ha, Andrew M. Dai, and Quoc V. Le. 2017. HyperNetworks. In 5th International Conference on Learning Representations, ICLR 2017."},{"key":"e_1_3_2_1_15_1","volume-title":"An Empirical Investigation of 3D Anomaly Detection and Segmentation. arXiv preprint arXiv:2203.05550","author":"Horwitz Eliahu","year":"2022","unstructured":"Eliahu Horwitz and Yedid Hoshen. 2022. An Empirical Investigation of 3D Anomaly Detection and Segmentation. arXiv preprint arXiv:2203.05550 (2022)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00298"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428370"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3199228"},{"key":"e_1_3_2_1_19_1","volume-title":"Multimodal Prompting with Missing Modalities for Visual Recognition. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Lee Yi-Lun","year":"2023","unstructured":"Yi-Lun Lee, Yi-Hsuan Tsai, Wei-Chen Chiu, and Chen-Yu Lee. 2023. Multimodal Prompting with Missing Modalities for Visual Recognition. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3293772"},{"key":"e_1_3_2_1_21_1","unstructured":"Jiang Liu Bolin Li Haoyuan Li Tianwei Lin Wenqiao Zhang Tao Zhong Zhelun Yu Jinghao Wei Hao Cheng Wanggui He Fangxun Shu Hao Jiang Zheqi Lv Juncheng Li Siliang Tang and Yueting Zhuang. 2025. Boosting Private Domain Understanding of Efficient MLLMs: A Tuning-free Adaptive Universal Prompt Optimization Framework. arXiv:2412.19684 [cs.AI] https:\/\/arxiv.org\/abs\/2412.19684"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01764"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16330"},{"key":"e_1_3_2_1_24_1","first-page":"604","volume-title":"Tel Aviv","author":"Pang Yatian","year":"2022","unstructured":"Yatian Pang, Wenxiao Wang, Francis EH Tay, Wei Liu, Yonghong Tian, and Li Yuan. 2022. Masked autoencoders for point cloud self-supervised learning. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part II. Springer, 604-621."},{"key":"e_1_3_2_1_25_1","volume-title":"Advances in Neural Information Processing Systems","author":"Qi Charles Ruizhongtai","year":"2017","unstructured":"Charles Ruizhongtai Qi, Li Yi, Hao Su, and Leonidas J Guibas. 2017. PointNet: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/d8bf84be3800d12f74d8b05e9b89836f-Paper.pdf"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3535317"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01392"},{"key":"e_1_3_2_1_28_1","volume-title":"Towards Total Recall in Industrial Anomaly Detection. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 14318-14328","author":"Roth Karsten","year":"2022","unstructured":"Karsten Roth, Latha Pemula, Joaquin Zepeda, Bernhard Sch\u00f6lkopf, Thomas Brox, and Peter Gehler. 2022b. Towards Total Recall in Industrial Anomaly Detection. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 14318-14328."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01466"},{"key":"e_1_3_2_1_30_1","volume-title":"AnoSeg: Anomaly segmentation network using self-supervised learning. arXiv preprint arXiv:2110.03396","author":"Song Jouwon","year":"2021","unstructured":"Jouwon Song, Kyeongbo Kong, Ye-In Park, Seong-Gyun Kim, and Suk-Ju Kang. 2021. AnoSeg: Anomaly segmentation network using self-supervised learning. arXiv preprint arXiv:2110.03396 (2021)."},{"key":"e_1_3_2_1_31_1","unstructured":"Wenbo Sui Daniel Lichau Josselin Lef\u00e8vre and Harold Phelippeau. 2024. Incomplete Multimodal Industrial Anomaly Detection via Cross-Modal Distillation. arXiv:2405.13571 [cs.CV] https:\/\/arxiv.org\/abs\/2405.13571"},{"key":"e_1_3_2_1_32_1","volume-title":"Representation Learning with Contrastive Predictive Coding. ArXiv","author":"van den Oord A\u00e4ron","year":"2018","unstructured":"A\u00e4ron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation Learning with Contrastive Predictive Coding. ArXiv, Vol. abs\/1807.03748 (2018). https:\/\/api.semanticscholar.org\/CorpusID:49670925"},{"key":"e_1_3_2_1_33_1","volume-title":"Learning cross-modality representations from multi-modal images","author":"van Tulder Gijs","year":"2018","unstructured":"Gijs van Tulder and Marleen de Bruijne. 2018. Learning cross-modality representations from multi-modal images. IEEE transactions on medical imaging, Vol. 38, 2 (2018), 638-648."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01524"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00776"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Shun Wei Jielin Jiang and Xiaolong Xu. 2025. UniNet: A Contrastive Learning-guided Unified Framework with Feature Selection for Anomaly Detection. (2025).","DOI":"10.1109\/CVPR52734.2025.00934"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01919"},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Association for Computational Linguistics, Online, 38-45","author":"Wolf Thomas","year":"2020","unstructured":"Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, R\u00e9mi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lhoest, and Alexander M. Rush. 2020. Transformers: State-of-the-Art Natural Language Processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Association for Computational Linguistics, Online, 38-45. https:\/\/www.aclweb.org\/anthology\/2020.emnlp-demos.6"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00080"},{"key":"e_1_3_2_1_40_1","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:2502.07601 [cs.CV] https:\/\/arxiv.org\/abs\/2502.07601"},{"key":"e_1_3_2_1_41_1","volume-title":"Customizing Visual-Language Foundation Models for Multi-modal Anomaly Detection and Reasoning. arXiv preprint arXiv:2403.11083","author":"Xu Xiaohao","year":"2024","unstructured":"Xiaohao Xu, Yunkang Cao, Yongqi Chen, Weiming Shen, and Xiaonan Huang. 2024. Customizing Visual-Language Foundation Models for Multi-modal Anomaly Detection and Reasoning. arXiv preprint arXiv:2403.11083 (2024)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539388"},{"key":"e_1_3_2_1_44_1","first-page":"54716","volume-title":"Levine (Eds.)","volume":"36","author":"Zhang Yunhua","year":"2023","unstructured":"Yunhua Zhang, Hazel Doughty, and Cees Snoek. 2023. Learning Unseen Modality Interaction. In Advances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 54716-54726. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/abb4847bbd60f38b1b7649d26c7a0067-Paper-Conference.pdf"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.04.020"}],"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\/3746027.3754766","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:03:23Z","timestamp":1765343003000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754766"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":45,"alternative-id":["10.1145\/3746027.3754766","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754766","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"}}]}}