{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T14:00:39Z","timestamp":1784210439121,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100010040","name":"Taishan Scholar Project of Shandong Province","doi-asserted-by":"publisher","award":["tsqn202306079"],"award-info":[{"award-number":["tsqn202306079"]}],"id":[{"id":"10.13039\/501100010040","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62471278"],"award-info":[{"award-number":["62471278"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Grants Council of the Hong Kong Special Administrative Region, China","award":["STG5\/E-103\/24-R"],"award-info":[{"award-number":["STG5\/E-103\/24-R"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755131","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:30:51Z","timestamp":1761377451000},"page":"343-352","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["UIS-Mamba: Exploring Mamba for Underwater Instance Segmentation via Dynamic Tree Scan and Hidden State Weaken"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0972-4008","authenticated-orcid":false,"given":"Runmin","family":"Cong","sequence":"first","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, Shandong, China and Key Laboratory of Machine Intelligence and System Control, Ministry of Education, Jinan, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4146-6535","authenticated-orcid":false,"given":"Zongji","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, Shandong, China and Key Laboratory of Machine Intelligence and System Control, Ministry of Education, Jinan, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8846-8294","authenticated-orcid":false,"given":"Hao","family":"Fang","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, Shandong, China and Key Laboratory of Machine Intelligence and System Control, Ministry of Education, Jinan, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9373-9685","authenticated-orcid":false,"given":"Haoyan","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, Shandong, China and Key Laboratory of Machine Intelligence and System Control, Ministry of Education, Jinan, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7484-7261","authenticated-orcid":false,"given":"Sam","family":"Kwong","sequence":"additional","affiliation":[{"name":"School of Data Science, Lingnan University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"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\/CVPR.2017.68"},{"key":"e_1_3_2_1_2_1","first-page":"37","volume-title":"Scienc. Natur. Moravicae)","volume":"3","author":"Boruvka Otakar","year":"1926","unstructured":"Otakar Boruvka. 1926. O jist\u00e9m probl\u00e9mu minim\u00e1ln\u00edm. Pr\u00e1ce Mor. Prirodved. Spol. v Brne (Acta Societ. Scienc. Natur. Moravicae), Vol. 3, 3 (1926), 37-58."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"e_1_3_2_1_4_1","volume-title":"RSPrompter: Learning to prompt for remote sensing instance segmentation based on visual foundation model","author":"Chen Keyan","year":"2024","unstructured":"Keyan Chen, Chenyang Liu, Hao Chen, Haotian Zhang, Wenyuan Li, Zhengxia Zou, and Zhenwei Shi. 2024. RSPrompter: Learning to prompt for remote sensing instance segmentation based on visual foundation model. IEEE Transactions on Geoscience and Remote Sensing (2024)."},{"key":"e_1_3_2_1_5_1","unstructured":"Kai Chen Jiaqi Wang Jiangmiao Pang Y Cao Y Xiong X Li S Sun W Feng Z Liu J Xu et al. 1906. MMDetection: Open mmlab detection toolbox and benchmark. arXiv 2019. arXiv preprint arXiv:1906.07155 (1906)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_39"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3286263"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-023-00019-6"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00626"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01290"},{"key":"e_1_3_2_1_14_1","volume-title":"European Conference on Computer Vision. Springer, 225-241","author":"Fang Hao","year":"2024","unstructured":"Hao Fang, Peng Wu, Yawei Li, Xinxin Zhang, and Xiankai Lu. 2024a. Unified embedding alignment for open-vocabulary video instance segmentation. In European Conference on Computer Vision. Springer, 225-241."},{"key":"e_1_3_2_1_15_1","volume-title":"Learning better video query with sam for video instance segmentation","author":"Fang Hao","year":"2024","unstructured":"Hao Fang, Tong Zhang, Xiaofei Zhou, and Xinxin Zhang. 2024b. Learning better video query with sam for video instance segmentation. IEEE Transactions on Circuits and Systems for Video Technology (2024)."},{"key":"e_1_3_2_1_16_1","volume-title":"Hungry hungry hippos: Towards language modeling with state space models. arXiv preprint arXiv:2212.14052","author":"Fu Daniel Y","year":"2022","unstructured":"Daniel Y Fu, Tri Dao, Khaled K Saab, Armin W Thomas, Atri Rudra, and Christopher R\u00e9. 2022. Hungry hungry hippos: Towards language modeling with state space models. arXiv preprint arXiv:2212.14052 (2022)."},{"key":"e_1_3_2_1_17_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_18_1","volume-title":"Efficiently modeling long sequences with structured state spaces. arXiv preprint arXiv:2111.00396","author":"Gu Albert","year":"2021","unstructured":"Albert Gu, Karan Goel, and Christopher R\u00e9. 2021a. Efficiently modeling long sequences with structured state spaces. arXiv preprint arXiv:2111.00396 (2021)."},{"key":"e_1_3_2_1_19_1","volume-title":"Combining recurrent, convolutional, and continuous-time models with linear state space layers. Advances in neural information processing systems","author":"Gu Albert","year":"2021","unstructured":"Albert Gu, Isys Johnson, Karan Goel, Khaled Saab, Tri Dao, Atri Rudra, and Christopher R\u00e9. 2021b. Combining recurrent, convolutional, and continuous-time models with linear state space layers. Advances in neural information processing systems, Vol. 34 (2021), 572-585."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128076"},{"key":"e_1_3_2_1_21_1","volume-title":"European conference on computer vision. Springer, 222-241","author":"Guo Hang","year":"2024","unstructured":"Hang Guo, Jinmin Li, Tao Dai, Zhihao Ouyang, Xudong Ren, and Shu-Tao Xia. 2024. Mambair: A simple baseline for image restoration with state-space model. In European conference on computer vision. Springer, 222-241."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_24_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. 2024. Localmamba: Visual state space model with windowed selective scan. arXiv preprint arXiv:2403.09338 (2024)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00657"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164918"},{"key":"e_1_3_2_1_27_1","volume-title":"Underwater salient object detection via dual-stage self-paced learning and depth emphasis","author":"Jin Jianhui","year":"2024","unstructured":"Jianhui Jin, Qiuping Jiang, Qingyuan Wu, Binwei Xu, and Runmin Cong. 2024. Underwater salient object detection via dual-stage self-paced learning and depth emphasis. IEEE Transactions on Circuits and Systems for Video Technology (2024)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2025.105413"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC58517.2023.10317279"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00437"},{"key":"e_1_3_2_1_31_1","volume-title":"Segment Anything. In Proceedings of the IEEE\/CVF international conference on computer vision. 4015-4026","author":"Kirillov Alexander","year":"2023","unstructured":"Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C. Berg, Wan-Yen Lo, Piotr Dollar, and Ross Girshick. 2023. Segment Anything. In Proceedings of the IEEE\/CVF international conference on computer vision. 4015-4026."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"e_1_3_2_1_33_1","volume-title":"Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems","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, Vol. 25 (2012)."},{"key":"e_1_3_2_1_34_1","volume-title":"An underwater image enhancement benchmark dataset and beyond","author":"Li Chongyi","year":"2019","unstructured":"Chongyi Li, Chunle Guo, Wenqi Ren, Runmin Cong, Junhui Hou, Sam Kwong, and Dacheng Tao. 2019. An underwater image enhancement benchmark dataset and beyond. IEEE transactions on image processing, Vol. 29 (2019), 4376-4389."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00126"},{"key":"e_1_3_2_1_36_1","volume-title":"Sam Kwong, and Runmin Cong.","author":"Lian Shijie","year":"2024","unstructured":"Shijie Lian, Ziyi Zhang, Hua Li, Wenjie Li, Laurence Tianruo Yang, Sam Kwong, and Runmin Cong. 2024. Diving into underwater: Segment anything model guided underwater salient instance segmentation and a large-scale dataset. arXiv preprint arXiv:2406.06039 (2024)."},{"key":"e_1_3_2_1_37_1","first-page":"740","volume-title":"proceedings, part v 13","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer vision-ECCV 2014: 13th European conference, zurich, Switzerland, September 6-12, proceedings, part v 13. Springer, 740-755."},{"key":"e_1_3_2_1_38_1","volume-title":"Vmamba: Visual state space model. Advances in neural information processing systems","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, Vol. 37 (2024), 103031-103063."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01776"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141891"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-89128-2_46"},{"key":"e_1_3_2_1_43_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_44_1","volume-title":"Sigma: Siamese mamba network for multi-modal semantic segmentation. arXiv preprint arXiv:2404.04256","author":"Wan Zifu","year":"2024","unstructured":"Zifu Wan, Pingping Zhang, Yuhao Wang, Silong Yong, Simon Stepputtis, Katia Sycara, and Yaqi Xie. 2024. Sigma: Siamese mamba network for multi-modal semantic segmentation. arXiv preprint arXiv:2404.04256 (2024)."},{"key":"e_1_3_2_1_45_1","volume-title":"Underwater image quality optimization: Researches, challenges, and future trends. Image and Vision Computing","author":"Wang Mingjie","year":"2024","unstructured":"Mingjie Wang, Keke Zhang, Hongan Wei, Weiling Chen, and Tiesong Zhao. 2024. Underwater image quality optimization: Researches, challenges, and future trends. Image and Vision Computing (2024), 104995."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01414"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Robert L Williams Douglas A Lawrence et al. 2007. Linear state-space control systems. John Wiley & Sons.","DOI":"10.1002\/9780470117873"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3065822"},{"key":"e_1_3_2_1_49_1","volume-title":"The Thirteenth International Conference on Learning Representations.","author":"Xiao Chaodong","year":"2025","unstructured":"Chaodong Xiao, Minghan Li, Zhengqiang Zhang, Deyu Meng, and Lei Zhang. 2025. Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_50_1","volume-title":"Grootvl: Tree topology is all you need in state space model. arXiv preprint arXiv:2406.02395","author":"Xiao Yicheng","year":"2024","unstructured":"Yicheng Xiao, Lin Song, Shaoli Huang, Jiangshan Wang, Siyu Song, Yixiao Ge, Xiu Li, and Ying Shan. 2024. Grootvl: Tree topology is all you need in state space model. arXiv preprint arXiv:2406.02395 (2024)."},{"key":"e_1_3_2_1_51_1","volume-title":"Plainmamba: Improving non-hierarchical mamba in visual recognition. arXiv preprint arXiv:2403.17695","author":"Yang Chenhongyi","year":"2024","unstructured":"Chenhongyi Yang, Zehui Chen, Miguel Espinosa, Linus Ericsson, Zhenyu Wang, Jiaming Liu, and Elliot J Crowley. 2024. Plainmamba: Improving non-hierarchical mamba in visual recognition. arXiv preprint arXiv:2403.17695 (2024)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2353642"},{"key":"e_1_3_2_1_53_1","volume-title":"Towards underwater camouflaged object tracking: An experimental evaluation of sam and sam 2. arXiv preprint arXiv:2409.16902","author":"Zhang Chunhui","year":"2024","unstructured":"Chunhui Zhang, Li Liu, Guanjie Huang, Hao Wen, Xi Zhou, and Yanfeng Wang. 2024b. Towards underwater camouflaged object tracking: An experimental evaluation of sam and sam 2. arXiv preprint arXiv:2409.16902 (2024)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3387696"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMA49215.2020.9233698"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3124814"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2021.3132082","article-title":"Dense attention-guided cascaded network for salient object detection of strip steel surface defects","volume":"71","author":"Zhou Xiaofei","year":"2021","unstructured":"Xiaofei Zhou, Hao Fang, Zhi Liu, Bolun Zheng, Yaoqi Sun, Jiyong Zhang, and Chenggang Yan. 2021b. Dense attention-guided cascaded network for salient object detection of strip steel surface defects. IEEE Transactions on Instrumentation and Measurement, Vol. 71 (2021), 1-14.","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"e_1_3_2_1_58_1","volume-title":"CA-Net: Cascaded adaptive network for underwater image enhancement","author":"Zhou Xiaofei","year":"2025","unstructured":"Xiaofei Zhou, Ming Peng, Qiuping Jiang, Runmin Cong, Jiyong Wang, and Yun Chen. 2025. CA-Net: Cascaded adaptive network for underwater image enhancement. IEEE Journal of Oceanic Engineering (2025)."},{"key":"e_1_3_2_1_59_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)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"}],"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\/3746027.3755131","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T20:01:55Z","timestamp":1765310515000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755131"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":60,"alternative-id":["10.1145\/3746027.3755131","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755131","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"}}]}}