{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:05:04Z","timestamp":1765339504393,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62273241"],"award-info":[{"award-number":["62273241"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2024A1515011946"],"award-info":[{"award-number":["2024A1515011946"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hong Kong RGC Collaborative Research Fund","award":["C5055-24G"],"award-info":[{"award-number":["C5055-24G"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754876","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:55:00Z","timestamp":1761375300000},"page":"3261-3269","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["EchoVim: Making Vision Mamba Docile for Echocardiography Video Segmentation via Dynamic Interaction and Semantic Token-attentive Refinement"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2218-591X","authenticated-orcid":false,"given":"Jingxing","family":"Guo","sequence":"first","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4981-7529","authenticated-orcid":false,"given":"Guilian","family":"Chen","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7011-1729","authenticated-orcid":false,"given":"Yimu","family":"Sun","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0399-9089","authenticated-orcid":false,"given":"Huisi","family":"Wu","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7059-0929","authenticated-orcid":false,"given":"Jing","family":"Qin","sequence":"additional","affiliation":[{"name":"Hong Kong Polytechnic University, Hong Kong, China"}]}],"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\/ACCESS.2021.3122256"},{"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":"10.3389\/fcvm.2020.00025"},{"volume-title":"Medical Imaging 2021: Image Processing","author":"Chen Yida","key":"e_1_3_2_1_4_1","unstructured":"Yida Chen, Xiaoyan Zhang, Christopher M Haggerty, and Joshua V Stough. 2021. Assessing the generalizability of temporally coherent echocardiography video segmentation. In Medical Imaging 2021: Image Processing, Vol. 11596. SPIE, 463-469."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00919"},{"key":"e_1_3_2_1_7_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_8_1","doi-asserted-by":"publisher","DOI":"10.1161\/01.CIR.60.4.760"},{"key":"e_1_3_2_1_9_1","volume-title":"Desam: Decoupling segment anything model for generalizable medical image segmentation. arXiv preprint arXiv:2306.00499","author":"Gao Yifan","year":"2023","unstructured":"Yifan Gao, Wei Xia, Dingdu Hu, and Xin Gao. 2023. Desam: Decoupling segment anything model for generalizable medical image segmentation. arXiv preprint arXiv:2306.00499 (2023)."},{"key":"e_1_3_2_1_10_1","volume-title":"PV-LVNet: Direct left ventricle multitype indices estimation from 2D echocardiograms of paired apical views with deep neural networks. Medical image analysis","author":"Ge Rongjun","year":"2019","unstructured":"Rongjun Ge, Guanyu Yang, Yang Chen, Limin Luo, Cheng Feng, Heye Zhang, and Shuo Li. 2019. PV-LVNet: Direct left ventricle multitype indices estimation from 2D echocardiograms of paired apical views with deep neural networks. Medical image analysis, Vol. 58 (2019), 101554."},{"key":"e_1_3_2_1_11_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_12_1","volume-title":"Accuracy of segment-anything model (sam) in medical image segmentation tasks. arXiv preprint arXiv:2304.09324","author":"He Sheng","year":"2023","unstructured":"Sheng He, Rina Bao, Jingpeng Li, P Ellen Grant, and Yangming Ou. 2023. Accuracy of segment-anything model (sam) in medical image segmentation tasks. arXiv preprint arXiv:2304.09324, Vol. 2 (2023)."},{"key":"e_1_3_2_1_13_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861","author":"Howard Andrew G","year":"2017","unstructured":"Andrew G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)."},{"key":"e_1_3_2_1_14_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_15_1","volume-title":"Localmamba: Visual state space model with windowed selective scan. arXiv preprint arXiv:2403.09338","author":"Huang Tao","year":"2024","unstructured":"Tao Huang, Xiaohuan Pei, Shan You, Fei Wang, Chen Qian, and Chang Xu. 2024a. Localmamba: Visual state space model with windowed selective scan. arXiv preprint arXiv:2403.09338 (2024)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.103061"},{"key":"e_1_3_2_1_17_1","volume-title":"Medivista-sam: Zero-shot medical video analysis with spatio-temporal sam adaptation. arXiv preprint arXiv:2309.13539","author":"Kim Sekeun","year":"2023","unstructured":"Sekeun Kim, Kyungsang Kim, Jiang Hu, Cheng Chen, Zhiliang Lyu, Ren Hui, Sunghwan Kim, Zhengliang Liu, Aoxiao Zhong, Xiang Li, et al., 2023. Medivista-sam: Zero-shot medical video analysis with spatio-temporal sam adaptation. arXiv preprint arXiv:2309.13539 (2023)."},{"key":"e_1_3_2_1_18_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"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","volume-title":"Pierre-Marc Jodoin, Thomas Grenier, et al.","author":"Leclerc Sarah","year":"2019","unstructured":"Sarah Leclerc, Erik Smistad, Joao Pedrosa, Andreas \u00d8stvik, Frederic Cervenansky, Florian Espinosa, Torvald Espeland, Erik Andreas Rye Berg, Pierre-Marc Jodoin, Thomas Grenier, et al., 2019. Deep learning for segmentation using an open large-scale dataset in 2D echocardiography. IEEE transactions on medical imaging, Vol. 38, 9 (2019), 2198-2210."},{"key":"e_1_3_2_1_21_1","volume-title":"European conference on computer vision. Springer, 237-255","author":"Li Kunchang","year":"2024","unstructured":"Kunchang Li, Xinhao Li, Yi Wang, Yinan He, Yali Wang, Limin Wang, and Yu Qiao. 2024a. Videomamba: State space model for efficient video understanding. In European conference on computer vision. Springer, 237-255."},{"key":"e_1_3_2_1_22_1","volume-title":"Mamba-nd: Selective state space modeling for multi-dimensional data. arXiv preprint arXiv:2402.05892","author":"Li Shufan","year":"2024","unstructured":"Shufan Li, Harkanwar Singh, and Aditya Grover. 2024b. Mamba-nd: Selective state space modeling for multi-dimensional data. arXiv preprint arXiv:2402.05892 (2024)."},{"key":"e_1_3_2_1_23_1","volume-title":"SAMUS: Adapting segment anything model for clinically-friendly and generalizable ultrasound image segmentation. arXiv preprint arXiv:2309.06824","author":"Lin Xian","year":"2023","unstructured":"Xian Lin, Yangyang Xiang, Li Zhang, Xin Yang, Zengqiang Yan, and Li Yu. 2023. SAMUS: Adapting segment anything model for clinically-friendly and generalizable ultrasound image segmentation. arXiv preprint arXiv:2309.06824 (2023)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101873"},{"key":"e_1_3_2_1_25_1","volume-title":"VMamba: Visual State Space Model. arXiv preprint arXiv:2401.10166","author":"Liu Yue","year":"2024","unstructured":"Yue Liu, Yunjie Tian, Yuzhong Zhao, Hongtian Yu, Lingxi Xie, Yaowei Wang, Qixiang Ye, and Yunfan Liu. 2024. VMamba: Visual State Space Model. arXiv preprint arXiv:2401.10166 (2024)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"e_1_3_2_1_27_1","first-page":"565","article-title":"V-net: Fully convolutional neural networks for volumetric medical image segmentation. In 2016 fourth international conference on 3D vision (3DV)","author":"Milletari Fausto","year":"2016","unstructured":"Fausto Milletari, Nassir Navab, and Seyed-Ahmad Ahmadi. 2016. V-net: Fully convolutional neural networks for volumetric medical image segmentation. In 2016 fourth international conference on 3D vision (3DV). Ieee, 565-571.","journal-title":"Ieee"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2145-8"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3173669"},{"key":"e_1_3_2_1_30_1","volume-title":"Efficientvmamba: Atrous selective scan for light weight visual mamba. arXiv preprint arXiv:2403.09977","author":"Pei Xiaohuan","year":"2024","unstructured":"Xiaohuan Pei, Tao Huang, and Chang Xu. 2024. Efficientvmamba: Atrous selective scan for light weight visual mamba. arXiv preprint arXiv:2403.09977 (2024)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16440-8_37"},{"key":"e_1_3_2_1_32_1","volume-title":"Mlp-mixer: An all-mlp architecture for vision. Advances in neural information processing systems","author":"Tolstikhin Ilya O","year":"2021","unstructured":"Ilya O Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Thomas Unterthiner, Jessica Yung, Andreas Steiner, Daniel Keysers, Jakob Uszkoreit, et al., 2021. Mlp-mixer: An all-mlp architecture for vision. Advances in neural information processing systems, Vol. 34 (2021), 24261-24272."},{"key":"e_1_3_2_1_33_1","volume-title":"Hieu Pham Huy, and Long Tran Quoc","author":"Van Phi Nguyen","year":"2023","unstructured":"Phi Nguyen Van, Hieu Pham Huy, and Long Tran Quoc. 2023. Echocardiography segmentation using neural ode-based diffeomorphic registration field. arXiv preprint arXiv:2306.09687 (2023)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25381"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102397"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102397"},{"key":"e_1_3_2_1_37_1","volume-title":"Medical sam adapter: Adapting segment anything model for medical image segmentation. arXiv","author":"Wu J","year":"2023","unstructured":"J Wu, Y Zhang, R Fu, H Fang, Y Liu, Z Wang, Y Xu, and Y Jin. 2023c. Medical sam adapter: Adapting segment anything model for medical image segmentation. arXiv 2023. arXiv preprint arXiv:2304.12620 (2023)."},{"key":"e_1_3_2_1_38_1","volume-title":"Chan","author":"Wu Qiangqiang","year":"2023","unstructured":"Qiangqiang Wu, Tianyu Yang, Wei Wu, and Antoni B. Chan. 2023b. Scalable Video Object Segmentation with Simplified Framework. In ICCV."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3221429"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00224"},{"key":"e_1_3_2_1_41_1","volume-title":"P-mamba: Marrying perona malik diffusion with mamba for efficient pediatric echocardiographic left ventricular segmentation. arXiv preprint arXiv:2402.08506","author":"Ye Zi","year":"2024","unstructured":"Zi Ye and Tianxiang Chen. 2024. P-mamba: Marrying perona malik diffusion with mamba for efficient pediatric echocardiographic left ventricular segmentation. arXiv preprint arXiv:2402.08506 (2024)."},{"key":"e_1_3_2_1_42_1","volume-title":"MambaOut: Do We Really Need Mamba for Vision? arXiv preprint arXiv:2405.07992","author":"Yu Weihao","year":"2024","unstructured":"Weihao Yu and Xinchao Wang. 2024. MambaOut: Do We Really Need Mamba for Vision? arXiv preprint arXiv:2405.07992 (2024)."},{"key":"e_1_3_2_1_43_1","volume-title":"Real-time echocardiography image analysis and quantification of cardiac indices. Medical image analysis","author":"Zamzmi Ghada","year":"2022","unstructured":"Ghada Zamzmi, Sivaramakrishnan Rajaraman, Li-Yueh Hsu, Vandana Sachdev, and Sameer Antani. 2022. Real-time echocardiography image analysis and quantification of cardiac indices. Medical image analysis, Vol. 80 (2022), 102438."},{"key":"e_1_3_2_1_44_1","volume-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model. arXiv preprint arXiv:2401.09417","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. arXiv preprint arXiv:2401.09417 (2024)."}],"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\/3746027.3754876","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:01:40Z","timestamp":1765339300000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754876"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":44,"alternative-id":["10.1145\/3746027.3754876","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754876","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"}}]}}