{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T16:07:38Z","timestamp":1780675658753,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","funder":[{"name":"National Natural Science Foun- dation of China (NSFC)","award":["62306064"],"award-info":[{"award-number":["62306064"]}]},{"name":"Central- Guided Local Science and Technology Development","award":["2023ZYD0165"],"award-info":[{"award-number":["2023ZYD0165"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792498","type":"proceedings-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T12:38:33Z","timestamp":1777293513000},"page":"7330-7341","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Anchor Drift No More: Hierarchical Consistency-Guided Prompt Distillation for Incomplete Multimodal Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8944-6759","authenticated-orcid":false,"given":"Ruiting","family":"Dai","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China, ChengDu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7135-4172","authenticated-orcid":false,"given":"Zesen","family":"Cai","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, ChengDu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4742-4456","authenticated-orcid":false,"given":"Lisi","family":"Mo","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, ChengDu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4448-6906","authenticated-orcid":false,"given":"Guiduo","family":"Duan","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, ChengDu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9904-7295","authenticated-orcid":false,"given":"Keren","family":"Shi","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, ChengDu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8676-7429","authenticated-orcid":false,"given":"Tao","family":"He","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, ChengDu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.3390\/e26040320"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01791-0"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2024.3406422"},{"key":"e_1_3_2_1_5_1","volume-title":"Proc. ICLR","author":"Cicchetti Giordano","year":"2025","unstructured":"Giordano Cicchetti, Eleonora Grassucci, Luigi Sigillo, and Danilo Comminiello. 2025. Gramian multimodal representation learning and alignment. In Proc. ICLR 2025. Singapore."},{"key":"e_1_3_2_1_6_1","volume-title":"Proc. ICCV.","author":"Dai Ruiting","year":"2025","unstructured":"Ruiting Dai, Chenxi Li, Yandong Yan, Lisi Mo, Ke Qin, and Tao He. 2025. Unbiased Missing-modality Multimodal Learning. In Proc. ICCV."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112825"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447194"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27958"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.94"},{"key":"e_1_3_2_1_11_1","volume-title":"Semantic compositional learning for low-shot scene graph generation. arXiv preprint arXiv:2108.08600","author":"He Tao","year":"2021","unstructured":"Tao He, Lianli Gao, Jingkuan Song, Jianfei Cai, and Yuan-Fang Li. 2021b. Semantic compositional learning for low-shot scene graph generation. arXiv preprint arXiv:2108.08600 (2021)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3129280"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 15562-15572","author":"Hu Xin","year":"2025","unstructured":"Xin Hu, Ke Qin, Guiduo Duan, Ming Li, Yuan-Fang Li, and Tao He. 2025. SPADE: Spatial-Aware Denoising Network for Open-vocabulary Panoptic Scene Graph Generation with Long-and Local-range Context Reasoning. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 15562-15572."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29189"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589335.3651445"},{"key":"e_1_3_2_1_16_1","first-page":"25864","article-title":"Knowledge Bridger","author":"Ke Guanzhou","year":"2025","unstructured":"Guanzhou Ke, Shengfeng He, Xiaoli Wang, Bo Wang, Guoqing Chao, Yuanyang Zhang, Yi Xie, and Hexing Su. 2025b. Knowledge Bridger: Towards Training-Free Missing Modality Completion. In Proc. CVPR. 25864-25873.","journal-title":"Towards Training-Free Missing Modality Completion. In Proc. CVPR."},{"key":"e_1_3_2_1_17_1","volume-title":"Early warning of cryptocurrency reversal risks via multi-source data. Finance Research Letters","author":"Ke Zong","year":"2025","unstructured":"Zong Ke, Yuqing Cao, Zhenrui Chen, Yuchen Yin, Shouchao He, and Yu Cheng. 2025a. Early warning of cryptocurrency reversal risks via multi-source data. Finance Research Letters (2025), 107890."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i17.33984"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714606"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3347849"},{"key":"e_1_3_2_1_21_1","volume-title":"Mike Zheng Shou, and Shuicheng Yan","author":"Li Ming","year":"2023","unstructured":"Ming Li, Xiangyu Xu, Hehe Fan, Pan Zhou, Jun Liu, Jia-Wei Liu, Jiahe Li, Jussi Keppo, Mike Zheng Shou, and Shuicheng Yan. 2023b. STPrivacy: Spatio-temporal privacy-preserving action recognition. In ICCV."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01184"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234553"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00628"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02713"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2777"},{"key":"e_1_3_2_1_27_1","unstructured":"Yao Lu Ji Zhaiyuan Jiawei Du Yu Shanqing Qi Xuan and Joey Tianyi Zhou. [n.d.]. AutoAnnotator: A Collaborative Annotation Framework for Large and Small Language Models. Transactions on Machine Learning Research ([n.d.])."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3367532"},{"key":"e_1_3_2_1_29_1","volume-title":"Garnett (Eds.)","volume":"32","author":"M\u00fcller Rafael","year":"2019","unstructured":"Rafael M\u00fcller, Simon Kornblith, and Geoffrey E Hinton. 2019. When does label smoothing help?. In Advances in Neural Information Processing Systems, H. Wallach, H. Larochelle, A. Beygelzimer, F. dtextquotesingle Alch\u00e9-Buc, E. Fox, and R. Garnett (Eds.), Vol. 32. Curran Associates, Inc."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650285"},{"key":"e_1_3_2_1_31_1","first-page":"76214","volume-title":"Levine (Eds.)","volume":"36","author":"Wang Botao","year":"2023","unstructured":"Botao Wang, Jia Li, Yang Liu, Jiashun Cheng, Yu Rong, Wenjia Wang, and Fugee Tsung. 2023b. Deep Insights into Noisy Pseudo Labeling on Graph Data. 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., 76214-76228."},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the 32nd International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"1092","author":"Wang Weiran","year":"2015","unstructured":"Weiran Wang, Raman Arora, Karen Livescu, and Jeff Bilmes. 2015. On Deep Multi-View Representation Learning. In Proceedings of the 32nd International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 37). Lille, France, 1083-1092. https:\/\/proceedings.mlr.press\/v37\/wangb15.html"},{"key":"e_1_3_2_1_33_1","first-page":"17117","volume-title":"Levine (Eds.)","volume":"36","author":"Wang Yuanzhi","year":"2023","unstructured":"Yuanzhi Wang, Yong Li, and Zhen Cui. 2023a. Incomplete Multimodality-Diffused Emotion Recognition. 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., 17117-17128."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645359"},{"key":"e_1_3_2_1_35_1","first-page":"5102","article-title":"Distilled Prompt Learning for Incomplete Multimodal Survival Prediction","author":"Xu Yingxue","year":"2025","unstructured":"Yingxue Xu, Fengtao Zhou, Chenyu Zhao, Yihui Wang, Can Yang, and Hao Chen. 2025. Distilled Prompt Learning for Incomplete Multimodal Survival Prediction. In Proc. CVPR. 5102-5111.","journal-title":"Proc. CVPR."},{"key":"e_1_3_2_1_36_1","first-page":"59030","article-title":"Swift sampler: Efficient learning of sampler by 10 parameters","volume":"37","author":"Yao Jiawei","year":"2024","unstructured":"Jiawei Yao, Chuming Li, and Canran Xiao. 2024. Swift sampler: Efficient learning of sampler by 10 parameters. Advances in Neural Information Processing Systems, Vol. 37 (2024), 59030-59053.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_37_1","first-page":"3888","article-title":"Knowledge-Aligned Counterfactual-Enhancement Diffusion Perception for Unsupervised Cross-Domain Visual Emotion Recognition","author":"Yin Wen","year":"2025","unstructured":"Wen Yin, Yong Wang, Guiduo Duan, Dongyang Zhang, Xin Hu, Yuan-Fang Li, and Tao He. 2025. Knowledge-Aligned Counterfactual-Enhancement Diffusion Perception for Unsupervised Cross-Domain Visual Emotion Recognition. In Proc. CVPR. 3888-3898.","journal-title":"Proc. CVPR."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532064"},{"key":"e_1_3_2_1_40_1","volume-title":"FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving. arXiv preprint arXiv:2505.17685","author":"Zeng Shuang","year":"2025","unstructured":"Shuang Zeng, Xinyuan Chang, Mengwei Xie, Xinran Liu, Yifan Bai, Zheng Pan, Mu Xu, and Xing Wei. 2025. FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving. arXiv preprint arXiv:2505.17685 (2025)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3354382"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3424785"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.203"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00333"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3301933"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28591"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3593543"},{"key":"e_1_3_2_1_48_1","volume-title":"Dropping Experts","author":"Zhou Yixiao","year":"2025","unstructured":"Yixiao Zhou, Ziyu Zhao, Dongzhou Cheng, Zhiliang Wu, Jie Gui, Yi Yang, Fei Wu, Yu Cheng, and Hehe Fan. 2025. Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs. In Findings of the Association for Computational Linguistics: EMNLP 2025. 15169-15186."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447248"}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774904.3792498","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:53:06Z","timestamp":1780674786000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792498"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":49,"alternative-id":["10.1145\/3774904.3792498","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792498","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}