{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:41:39Z","timestamp":1765309299864,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755306","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:54:17Z","timestamp":1761375257000},"page":"6530-6539","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Probabilistic Mixture of Hyperbolic Mamba for Few-Shot Class-Incremental Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9337-687X","authenticated-orcid":false,"given":"Yawen","family":"Cui","sequence":"first","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7156-0115","authenticated-orcid":false,"given":"Wenbin","family":"Zou","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, Hong Kong and South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4612-5445","authenticated-orcid":false,"given":"Huiping","family":"Zhuang","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8659-4724","authenticated-orcid":false,"given":"Yi","family":"Wang","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4932-0593","authenticated-orcid":false,"given":"Lap-Pui","family":"Chau","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00435"},{"key":"e_1_3_2_1_2_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 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2025.3554028"},{"key":"e_1_3_2_1_4_1","unstructured":"Arslan Chaudhry Marc'Aurelio Ranzato Marcus Rohrbach and Mohamed Elhoseiny. 2018. Efficient Lifelong Learning with A-GEM. In ICLR."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01377"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers). 4171--4186."},{"key":"e_1_3_2_1_7_1","volume-title":"International conference on machine learning. PMLR, 5547--5569","author":"Du Nan","year":"2022","unstructured":"Nan Du, Yanping Huang, Andrew M Dai, Simon Tong, Dmitry Lepikhin, Yuanzhong Xu, Maxim Krikun, Yanqi Zhou, Adams Wei Yu, Orhan Firat, et al. 2022. Glam: Efficient scaling of language models with mixture-of-experts. In International conference on machine learning. PMLR, 5547--5569."},{"key":"e_1_3_2_1_8_1","volume-title":"international conference on machine learning. PMLR, 1050--1059","author":"Gal Yarin","year":"2016","unstructured":"Yarin Gal and Zoubin Ghahramani. 2016. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In international conference on machine learning. PMLR, 1050--1059."},{"key":"e_1_3_2_1_9_1","first-page":"6582","article-title":"Fecam: Exploiting the heterogeneity of class distributions in exemplar-free continual learning","volume":"36","author":"Goswami Dipam","year":"2023","unstructured":"Dipam Goswami, Yuyang Liu and Joost Van De Weijer. 2023. Fecam: Exploiting the heterogeneity of class distributions in exemplar-free continual learning. Advances in Neural Information Processing Systems 36 (2023), 6582--6595.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_10_1","volume-title":"Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752","author":"Gu Albert","year":"2023","unstructured":"Albert Gu and Tri Dao. 2023. Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)."},{"key":"e_1_3_2_1_11_1","unstructured":"Albert Gu Karan Goel and Christopher R\u00e9. 2022. Efficiently modeling long sequences with structured state spaces. In ICLR."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_13_1","volume-title":"Fortysecond International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=tH4Zka30JZ","author":"He Run","year":"2025","unstructured":"Run He, Di Fang, Yicheng Xu, Yawen Cui, Ming Li, Cen Chen, Ziqian Zeng, and Huiping Zhuang. 2025. Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental Learning. In Fortysecond International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=tH4Zka30JZ"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00885"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00395"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_25"},{"key":"e_1_3_2_1_17_1","unstructured":"Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_1_18_1","volume-title":"Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25 (2012)."},{"key":"e_1_3_2_1_19_1","volume-title":"Mamba-fscil: Dynamic adaptation with selective state space model for few-shot class-incremental learning. arXiv preprint arXiv:2407.06136","author":"Li Xiaojie","year":"2024","unstructured":"Xiaojie Li, Yibo Yang, JianlongWu, Bernard Ghanem, Liqiang Nie, and Min Zhang. 2024. Mamba-fscil: Dynamic adaptation with selective state space model for few-shot class-incremental learning. arXiv preprint arXiv:2407.06136 (2024)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_9"},{"key":"e_1_3_2_1_21_1","volume-title":"Vmamba: Visual state space model. Advances in neural information processing systems 37","author":"Liu Yue","year":"2024","unstructured":"Yue Liu, Yunjie Tian, Yuzhong Zhao, Hongtian Yu, Lingxi Xie, Yaowei Wang, Qixiang Ye, Jianbin Jiao, and Yunfan Liu. 2024. Vmamba: Visual state space model. Advances in neural information processing systems 37 (2024), 103031--103063."},{"key":"e_1_3_2_1_22_1","volume-title":"Poincar\u00e9 embeddings for learning hierarchical representations. Advances in neural information processing systems 30","author":"Nickel Maximillian","year":"2017","unstructured":"Maximillian Nickel and Douwe Kiela. 2017. Poincar\u00e9 embeddings for learning hierarchical representations. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_23_1","volume-title":"CLOSER: Towards Better Representation Learning for Few-Shot Class-Incremental Learning. In European Conference on Computer Vision. Springer, 18--35","author":"Oh Junghun","year":"2024","unstructured":"Junghun Oh, Sungyong Baik, and Kyoung Mu Lee. 2024. CLOSER: Towards Better Representation Learning for Few-Shot Class-Incremental Learning. In European Conference on Computer Vision. Springer, 18--35."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_22"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3136921"},{"key":"e_1_3_2_1_26_1","first-page":"8583","article-title":"Scaling vision with sparse mixture of experts","volume":"34","author":"Riquelme Carlos","year":"2021","unstructured":"Carlos Riquelme, Joan Puigcerver, Basil Mustafa, Maxim Neumann, Rodolphe Jenatton, Andr\u00e9 Susano Pinto, Daniel Keysers, and Neil Houlsby. 2021. Scaling vision with sparse mixture of experts. Advances in Neural Information Processing Systems 34 (2021), 8583--8595.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02259"},{"key":"e_1_3_2_1_28_1","volume-title":"Overcoming catastrophic forgetting in incremental few-shot learning by finding flat minima. Advances in neural information processing systems 34","author":"Shi Guangyuan","year":"2021","unstructured":"Guangyuan Shi, Jiaxin Chen,Wenlong Zhang, Li-Ming Zhan, and Xiao-MingWu. 2021. Overcoming catastrophic forgetting in incremental few-shot learning by finding flat minima. Advances in neural information processing systems 34 (2021), 6747--6761."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02316"},{"key":"e_1_3_2_1_30_1","volume-title":"European Conference on Computer Vision. Springer, 108--128","author":"Tang Yu-Ming","year":"2024","unstructured":"Yu-Ming Tang, Yi-Xing Peng, Jingke Meng, and Wei-Shi Zheng. 2024. Rethinking few-shot class-incremental learning: Learning from yourself. In European Conference on Computer Vision. Springer, 108--128."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01220"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.10.039"},{"key":"e_1_3_2_1_33_1","unstructured":"Oriol Vinyals Charles Blundell Timothy Lillicrap Daan Wierstra et al. 2016. Matching networks for one shot learning. In NeurPIS. 3630--3638."},{"key":"e_1_3_2_1_34_1","first-page":"50825","article-title":"Graph mixture of experts: Learning on large-scale graphs with explicit diversity modeling","volume":"36","author":"Wang Haotao","year":"2023","unstructured":"Haotao Wang, Ziyu Jiang, Yuning You, Yan Han, Gaowen Liu, Jayanth Srinivasa, Ramana Kompella, Zhangyang Wang, et al. 2023. Graph mixture of experts: Learning on large-scale graphs with explicit diversity modeling. Advances in Neural Information Processing Systems 36 (2023), 50825--50837.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_35_1","volume-title":"A comprehensive survey of continual learning: Theory, method and application","author":"Wang Liyuan","year":"2024","unstructured":"Liyuan Wang, Xingxing Zhang, Hang Su, and Jun Zhu. 2024. A comprehensive survey of continual learning: Theory, method and application. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)."},{"key":"e_1_3_2_1_36_1","first-page":"15060","article-title":"Few-shot class-incremental learning via training-free prototype calibration","volume":"36","author":"Wang Qi-Wei","year":"2023","unstructured":"Qi-Wei Wang, Da-Wei Zhou, Yi-Kai Zhang, De-Chuan Zhan, and Han-Jia Ye. 2023. Few-shot class-incremental learning via training-free prototype calibration. Advances in Neural Information Processing Systems 36 (2023), 15060--15076.","journal-title":"Advances in Neural Information Processing Systems"},{"volume-title":"Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental Learning. In The Eleventh International Conference on Learning Representations.","author":"Yang Yibo","key":"e_1_3_2_1_37_1","unstructured":"Yibo Yang, Haobo Yuan, Xiangtai Li, Zhouchen Lin, Philip Torr, and Dacheng Tao. [n. d.]. Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental Learning. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01227"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3133897"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01139"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00884"},{"key":"e_1_3_2_1_42_1","volume-title":"Deep class-incremental learning: A survey. arXiv preprint arXiv:2302.03648 1, 2","author":"Zhou Da-Wei","year":"2023","unstructured":"Da-Wei Zhou, Qi-Wei Wang, Zhi-Hong Qi, Han-Jia Ye, De-Chuan Zhan, and Ziwei Liu. 2023. Deep class-incremental learning: A survey. arXiv preprint arXiv:2302.03648 1, 2 (2023), 6."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3200865"},{"key":"e_1_3_2_1_44_1","first-page":"7103","article-title":"Mixture-of-experts with expert choice routing","volume":"35","author":"Zhou Yanqi","year":"2022","unstructured":"Yanqi Zhou, Tao Lei, Hanxiao Liu, Nan Du, Yanping Huang, Vincent Zhao, Andrew M Dai, Quoc V Le, James Laudon, et al. 2022. Mixture-of-experts with expert choice routing. Advances in Neural Information Processing Systems 35 (2022), 7103--7114.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00673"},{"key":"e_1_3_2_1_46_1","volume-title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model. In International Conference on Machine Learning. PMLR, 62429--62442","author":"Zhu Lianghui","year":"2024","unstructured":"Lianghui Zhu, Bencheng Liao, Qian Zhang, Xinlong Wang, Wenyu Liu, and Xinggang Wang. 2024. Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model. In International Conference on Machine Learning. PMLR, 62429--62442."},{"key":"e_1_3_2_1_47_1","volume-title":"Advances in Neural Information Processing Systems","author":"Zhuang Huiping","year":"2024","unstructured":"Huiping Zhuang, Yuchen Liu, Run He, Kai Tong, Ziqian Zeng, Cen Chen, Yi Wang, and Lap-Pui Chau. 2024. F-OAL: Forward-only Online Analytic Learning with Fast Training and Low Memory Footprint in Class Incremental Learning. In Advances in Neural Information Processing Systems, A. Globerson, L. Mackey, D. Belgrave, A. Fan, U. Paquet, J. Tomczak, and C. Zhang (Eds.), Vol. 37. Curran Associates, Inc., 41517--41538. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2024\/file\/48ffa38c13078d6ce26b328e7f373243-Paper-Conference.pdf"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00748"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00748"},{"key":"e_1_3_2_1_50_1","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Zhuang Huiping","year":"2022","unstructured":"Huiping Zhuang, Zhenyu Weng, Hongxin Wei, Renchunzi Xie, Kar-Ann Toh, and Zhiping Lin. 2022. ACIL: Analytic Class-Incremental Learning with Absolute Memorization and Privacy Protection. In Advances in Neural Information Processing Systems, Vol. 35. Curran Associates, Inc., 11602--11614."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755306","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:39:07Z","timestamp":1765309147000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755306"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":50,"alternative-id":["10.1145\/3746027.3755306","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755306","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"}}]}}