{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T00:13:42Z","timestamp":1778199222069,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":66,"publisher":"ACM","funder":[{"name":"The National Key Research and Development Program Inter-governmental Special Project for International Science and Technology Innovation Cooperation under grants","award":["2022YFE0112500"],"award-info":[{"award-number":["2022YFE0112500"]}]},{"name":"Foundation for Shenzhen Science and Technology Program under Grant","award":["JCYJ20240813151224032,JCYJ20240813151102004"],"award-info":[{"award-number":["JCYJ20240813151224032,JCYJ20240813151102004"]}]},{"name":"Shenzhen Medical Research Fund under Grant","award":["B2402030"],"award-info":[{"award-number":["B2402030"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755148","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:30:51Z","timestamp":1761377451000},"page":"7825-7834","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Unified Medical Image Segmentation with State Space Modeling Snake"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6793-1012","authenticated-orcid":false,"given":"Ruicheng","family":"Zhang","sequence":"first","affiliation":[{"name":"Sun Yat-Sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4611-7932","authenticated-orcid":false,"given":"Haowei","family":"Guo","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1006-8493","authenticated-orcid":false,"given":"Kanghui","family":"Tian","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4722-2183","authenticated-orcid":false,"given":"Jun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0586-4119","authenticated-orcid":false,"given":"Mingliang","family":"Yan","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8819-3741","authenticated-orcid":false,"given":"Zeyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Australian National University, Canberra, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4698-2658","authenticated-orcid":false,"given":"Shen","family":"Zhao","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University, Guangzhou, China"}],"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\/RBME.2021.3136343"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87231-1_19"},{"key":"e_1_3_2_1_3_1","volume-title":"Transunet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306","author":"Chen Jieneng","year":"2021","unstructured":"Jieneng Chen, Yongyi Lu, Qihang Yu, Xiangde Luo, Ehsan Adeli, Yan Wang, Le Lu, Alan L Yuille, and Yuyin Zhou. 2021a. Transunet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306 (2021)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01033"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3485721"},{"key":"e_1_3_2_1_6_1","unstructured":"Junlong Cheng Jin Ye Zhongying Deng Jianpin Chen Tianbin Li Haoyu Wang Yanzhou Su Ziyan Huang Jilong Chen Lei Jiang Hui Sun Junjun He Shaoting Zhang Min Zhu and Yu Qiao. 2023. SAM-Med2D. arXiv:2308.16184 [cs.CV] https:\/\/arxiv.org\/abs\/2308.16184"},{"key":"e_1_3_2_1_7_1","volume-title":"International Conference on Machine Learning (ICML).","author":"Dao Tri","year":"2024","unstructured":"Tri Dao and Albert Gu. 2024. Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality. In International Conference on Machine Learning (ICML)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103347"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2003.10778"},{"key":"e_1_3_2_1_10_1","volume-title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces. In First Conference on Language Modeling (COLM). https:\/\/openreview.net\/forum?id=tEYskw1VY2","author":"Gu Albert","year":"2024","unstructured":"Albert Gu and Tri Dao. 2024. Mamba: Linear-Time Sequence Modeling with Selective State Spaces. In First Conference on Language Modeling (COLM). https:\/\/openreview.net\/forum?id=tEYskw1VY2"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00138"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_1_14_1","volume-title":"Audio-visual controlled video diffusion with masked selective state spaces modeling for natural talking head generation. arXiv preprint arXiv:2504.02542","author":"Hong Fa-Ting","year":"2025","unstructured":"Fa-Ting Hong, Zunnan Xu, Zixiang Zhou, Jun Zhou, Xiu Li, Qin Lin, Qinglin Lu, and Dan Xu. 2025. Audio-visual controlled video diffusion with masked selective state spaces modeling for natural talking head generation. arXiv preprint arXiv:2504.02542 (2025)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01933"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01501"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00133570"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_21_1","volume-title":"Proc. MICCAI Multi-Atlas Labeling Beyond Cranial Vault-Workshop Challenge","volume":"5","author":"Landman Bennett","year":"2015","unstructured":"Bennett Landman, Zhoubing Xu, J Igelsias, Martin Styner, T Langerak, and Arno Klein. 2015. Miccai multi-atlas labeling beyond the cranial vault-workshop and challenge. In Proc. MICCAI Multi-Atlas Labeling Beyond Cranial Vault-Workshop Challenge, Vol. 5. 12."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00434"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-23911-3_21"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3151666"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00915"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00540"},{"key":"e_1_3_2_1_27_1","volume-title":"Mtanet: Multi-task attention network for automatic medical image segmentation and classification","author":"Ling Yating","year":"2023","unstructured":"Yating Ling, Yuling Wang, Wenli Dai, Jie Yu, Ping Liang, and Dexing Kong. 2023. Mtanet: Multi-task attention network for automatic medical image segmentation and classification. IEEE Transactions on Medical Imaging (2023)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-79244-y"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01934"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Rong Liu Junye Liang Jiaqi Yang Jiang He and Peng Zhu. 2025. Dual Classification Head Self-training Network for Cross-scene Hyperspectral Image Classification. https:\/\/api.semanticscholar.org\/CorpusID:276580523","DOI":"10.1109\/TGRS.2025.3636101"},{"key":"e_1_3_2_1_31_1","first-page":"103031","volume-title":"Zhang (Eds.)","volume":"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. 2024b. VMamba: Visual State Space Model. In Advances in Neural Information Processing Systems (NeurIPS), A. Globerson, L. Mackey, D. Belgrave, A. Fan, U. Paquet, J. Tomczak, and C. Zhang (Eds.), Vol. 37. Curran Associates, Inc., 103031-103063. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2024\/file\/baa2da9ae4bfed26520bb61d259a3653-Paper-Conference.pdf"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Xiangde Luo Zihan Li Shaoting Zhang Wenjun Liao and Guotai Wang. 2024. Rethinking Abdominal Organ Segmentation (RAOS) in\u00a0the\u00a0Clinical Scenario: A Robustness Evaluation Benchmark with\u00a0Challenging Cases. In International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) Marius George Linguraru Qi Dou Aasa Feragen Stamatia Giannarou Ben Glocker Karim Lekadir and Julia A. Schnabel (Eds.). Springer Nature Switzerland Cham 531-541.","DOI":"10.1007\/978-3-031-72114-4_51"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"e_1_3_2_1_34_1","first-page":"8167","article-title":"Cycoseg: A cyclic collaborative framework for automated medical image segmentation","volume":"44","author":"Medley Daniela O","year":"2021","unstructured":"Daniela O Medley, Carlos Santiago, and Jacinto C Nascimento. 2021. Cycoseg: A cyclic collaborative framework for automated medical image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44, 11 (2021), 8167-8182.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2023.102235"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00856"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"e_1_3_2_1_39_1","volume-title":"Learning Transferable Visual Models From Natural Language Supervision. In International Conference on Machine Learning (ICML) (Proceedings of Machine Learning Research","volume":"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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In International Conference on Machine Learning (ICML) (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 8748-8763. https:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-020-00715-8"},{"key":"e_1_3_2_1_41_1","volume-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Nassir Navab, Joachim Hornegger, William M","author":"Ronneberger Olaf","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Nassir Navab, Joachim Hornegger, William M. Wells, and Alejandro F. Frangi (Eds.). Springer International Publishing, Cham, 234-241."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102166"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118625"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2407.18559"},{"key":"e_1_3_2_1_45_1","volume-title":"International Conference on Machine Learning (ICML). https:\/\/api.semanticscholar.org\/CorpusID:232478903","author":"Tan Mingxing","unstructured":"Mingxing Tan and Quoc V. Le. 2021. EfficientNetV2: Smaller Models and Faster Training. In International Conference on Machine Learning (ICML). https:\/\/api.semanticscholar.org\/CorpusID:232478903"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102258"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87193-2_4"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ADICS58448.2024.10533619"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102581"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01221"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3215536"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2407.14153"},{"key":"e_1_3_2_1_53_1","volume-title":"Polyp-Mamba: Polyp Segmentation with Visual Mamba. In International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)","volume":"15008","author":"Xu Zhongxing","year":"2024","unstructured":"Zhongxing Xu, Feilong Tang, Zhe Chen, Zheng Zhou, Weishan Wu, Yuyao Yang, Yu Liang, Jiyu Jiang, Xuyue Cai, and Jionglong Su. 2024b. Polyp-Mamba: Polyp Segmentation with Visual Mamba. In International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Vol. LNCS 15008. Springer Nature Switzerland."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01109"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"crossref","unstructured":"Xianghua Ye Dazhou Guo Jia Ge Senxiang Yan Yi Xin Yuchen Song Yongheng Yan Bing-shen Huang Tsung-Min Hung Zhuotun Zhu et al. 2022. Comprehensive and clinically accurate head and neck cancer organs-at-risk delineation on a multi-institutional study. Nature communications Vol. 13 1 (2022) 6137.","DOI":"10.1038\/s41467-022-33178-z"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.11.055"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00255"},{"key":"e_1_3_2_1_58_1","volume-title":"CRISP-SAM2: SAM2 with Cross-Modal Interaction and Semantic Prompting for Multi-Organ Segmentation. arXiv preprint arXiv:2506.23121","author":"Yu Xinlei","year":"2025","unstructured":"Xinlei Yu, Changmiao Wang, Hui Jin, Ahmed Elazab, Gangyong Jia, Xiang Wan, Changqing Zou, and Ruiquan Ge. 2025. CRISP-SAM2: SAM2 with Cross-Modal Interaction and Semantic Prompting for Multi-Organ Segmentation. arXiv preprint arXiv:2506.23121 (2025)."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00381"},{"key":"e_1_3_2_1_60_1","volume-title":"GAMED-Snake: Gradient-aware Adaptive Momentum Evolution Deep Snake Model for Multi-organ Segmentation. arXiv preprint arXiv:2501.12844","author":"Zhang Ruicheng","year":"2025","unstructured":"Ruicheng Zhang, Haowei Guo, Zeyu Zhang, Puxin Yan, and Shen Zhao. 2025a. GAMED-Snake: Gradient-aware Adaptive Momentum Evolution Deep Snake Model for Multi-organ Segmentation. arXiv preprint arXiv:2501.12844 (2025)."},{"key":"e_1_3_2_1_61_1","volume-title":"Haowei Guo, and Puxin Yan.","author":"Zhang Ruicheng","year":"2025","unstructured":"Ruicheng Zhang, Yu Sun, Zeyu Zhang, Jinai Li, Xiaofan Liu, Au Hoi Fan, Haowei Guo, and Puxin Yan. 2025b. MARL-MambaContour: Unleashing Multi-Agent Deep Reinforcement Learning for Active Contour Optimization in Medical Image Segmentation. arXiv:2506.18679 [cs.CV] https:\/\/arxiv.org\/abs\/2506.18679"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/jbhi.2017.2776246"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102906"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102906"},{"key":"e_1_3_2_1_65_1","volume-title":"Objects as Points. ArXiv","author":"Zhou Xingyi","year":"2019","unstructured":"Xingyi Zhou, Dequan Wang, and Philipp Kr\u00e4henb\u00fchl. 2019. Objects as Points. ArXiv, Vol. abs\/1904.07850 (2019). https:\/\/api.semanticscholar.org\/CorpusID:118714035"},{"key":"e_1_3_2_1_66_1","volume-title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model. In International Conference on Machine Learning (ICML) (Proceedings of Machine Learning Research","volume":"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 (ICML) (Proceedings of Machine Learning Research, Vol. 235), Ruslan Salakhutdinov, Zico Kolter, Katherine Heller, Adrian Weller, Nuria Oliver, Jonathan Scarlett, and Felix Berkenkamp (Eds.). PMLR, 62429-62442. https:\/\/proceedings.mlr.press\/v235\/zhu24f.html"}],"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\/3746027.3755148","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:55:48Z","timestamp":1765310148000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755148"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":66,"alternative-id":["10.1145\/3746027.3755148","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755148","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"}}]}}