{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T05:42:47Z","timestamp":1785994967254,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":90,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Nansha Key Area Science and Technology Project","award":["2023ZD003"],"award-info":[{"award-number":["2023ZD003"]}]},{"name":"Guangzhou-HKUST(GZ) Joint Funding Program","award":["2023A03J0671, 2024A03J0618"],"award-info":[{"award-number":["2023A03J0671, 2024A03J0618"]}]},{"name":"Guangzhou Municipal Science and Technology Project","award":["2024A04J4230"],"award-info":[{"award-number":["2024A04J4230"]}]},{"name":"Guangzhou Industrial Information and Intelligent Key Laboratory Project","award":["2024A03J0628"],"award-info":[{"award-number":["2024A03J0628"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680916","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"7881-7890","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":55,"title":["RainMamba: Enhanced Locality Learning with State Space Models for Video Deraining"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4863-5119","authenticated-orcid":false,"given":"Hongtao","family":"Wu","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4083-5144","authenticated-orcid":false,"given":"Yijun","family":"Yang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7868-1100","authenticated-orcid":false,"given":"Huihui","family":"Xu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9068-0227","authenticated-orcid":false,"given":"Weiming","family":"Wang","sequence":"additional","affiliation":[{"name":"Hong Kong Metropolitan University, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9093-5648","authenticated-orcid":false,"given":"Jinni","family":"Zhou","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3871-663X","authenticated-orcid":false,"given":"Lei","family":"Zhu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou) & The Hong Kong University of Science and Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00286"},{"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":"10.1016\/S0304-3975(96)00259-9"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-30947-2_33"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-008-0200-2"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11006-006-0182-8"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00588"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.1994.413553"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01215"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00658"},{"key":"e_1_3_2_1_12_1","volume-title":"International conference on machine learning. PMLR, 1597--1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597--1607."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_42"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.236"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00571"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00206"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02467"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.186"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315077"},{"key":"e_1_3_2_1_20_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_21_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. 2021. Efficiently modeling long sequences with structured state spaces. arXiv preprint arXiv:2111.00396 (2021)."},{"key":"e_1_3_2_1_22_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. 2021. 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_23_1","volume-title":"MambaIR: A Simple Baseline for Image Restoration with State-Space Model. arXiv preprint arXiv:2402.15648","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. arXiv preprint arXiv:2402.15648 (2024)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00084"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3--662--38452--7_1"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00578"},{"key":"e_1_3_2_1_28_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_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/93597.98742"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2880512"},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings, Part II 14","author":"Johnson Justin","year":"2016","unstructured":"Justin Johnson, Alexandre Alahi, and Li Fei-Fei. 2016. Perceptual losses for real-time style transfer and super-resolution. In Computer Vision--ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11--14, 2016, Proceedings, Part II 14. Springer, 694--711."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Rudolph Emil Kalman. 1960. A new approach to linear filtering and prediction problems. (1960).","DOI":"10.1115\/1.3662552"},{"key":"e_1_3_2_1_33_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_34_1","volume-title":"VideoMamba: State Space Model for Efficient Video Understanding. arXiv preprint arXiv:2403.06977","author":"Li Kunchang","year":"2024","unstructured":"Kunchang Li, Xinhao Li, Yi Wang, Yinan He, Yali Wang, Limin Wang, and Yu Qiao. 2024. VideoMamba: State Space Model for Efficient Video Understanding. arXiv preprint arXiv:2403.06977 (2024)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00695"},{"key":"e_1_3_2_1_36_1","first-page":"378","article-title":"Recurrent video restoration transformer with guided deformable attention","volume":"35","author":"Liang Jingyun","year":"2022","unstructured":"Jingyun Liang, Yuchen Fan, Xiaoyu Xiang, Rakesh Ranjan, Eddy Ilg, Simon Green, Jiezhang Cao, Kai Zhang, Radu Timofte, and Luc V Gool. 2022. Recurrent video restoration transformer with guided deformable attention. Advances in Neural Information Processing Systems, Vol. 35 (2022), 378--393.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2007.11.002"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00074"},{"key":"e_1_3_2_1_39_1","volume-title":"Chen Change Loy, and Thomas S Huang","author":"Liu Ding","year":"2018","unstructured":"Ding Liu, Bihan Wen, Yuchen Fan, Chen Change Loy, and Thomas S Huang. 2018. Non-local recurrent network for image restoration. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00341"},{"key":"e_1_3_2_1_41_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_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1025196714293"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/69.908985"},{"key":"e_1_3_2_1_45_1","volume-title":"S4nd: Modeling images and videos as multidimensional signals with state spaces. Advances in neural information processing systems","author":"Nguyen Eric","year":"2022","unstructured":"Eric Nguyen, Karan Goel, Albert Gu, Gordon Downs, Preey Shah, Tri Dao, Stephen Baccus, and Christopher R\u00e9. 2022. S4nd: Modeling images and videos as multidimensional signals with state spaces. Advances in neural information processing systems, Vol. 35 (2022), 2846--2861."},{"key":"e_1_3_2_1_46_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00903"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00406"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02161-0"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.303"},{"key":"e_1_3_2_1_51_1","volume-title":"Space-filling curves","author":"Sagan Hans","unstructured":"Hans Sagan. 2012. Space-filling curves. Springer Science & Business Media."},{"key":"e_1_3_2_1_52_1","volume-title":"VmambaIR: Visual State Space Model for Image Restoration. arXiv preprint arXiv:2403.11423","author":"Shi Yuan","year":"2024","unstructured":"Yuan Shi, Bin Xia, Xiaoyu Jin, Xing Wang, Tianyu Zhao, Xin Xia, Xuefeng Xiao, and Wenming Yang. 2024. VmambaIR: Visual State Space Model for Image Restoration. arXiv preprint arXiv:2403.11423 (2024)."},{"key":"e_1_3_2_1_53_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3272283"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3412923"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161478"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3426953"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00994"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19800-7_33"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01255"},{"key":"e_1_3_2_1_61_1","volume-title":"Video-to-video synthesis. arXiv preprint arXiv:1808.06601","author":"Wang Ting-Chun","year":"2018","unstructured":"Ting-Chun Wang, Ming-Yu Liu, Jun-Yan Zhu, Guilin Liu, Andrew Tao, Jan Kautz, and Bryan Catanzaro. 2018. Video-to-video synthesis. arXiv preprint arXiv:1808.06601 (2018)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"e_1_3_2_1_63_1","volume-title":"Towards compact single image super-resolution via contrastive self-distillation. arXiv preprint arXiv:2105.11683","author":"Wang Yanbo","year":"2021","unstructured":"Yanbo Wang, Shaohui Lin, Yanyun Qu, Haiyan Wu, Zhizhong Zhang, Yuan Xie, and Angela Yao. 2021. Towards compact single image super-resolution via contrastive self-distillation. arXiv preprint arXiv:2105.11683 (2021)."},{"key":"e_1_3_2_1_64_1","volume-title":"Image quality assessment: from error visibility to structural similarity","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, Vol. 13, 4 (2004), 600--612."},{"key":"e_1_3_2_1_65_1","volume-title":"Video Waterdrop Removal via Spatio-Temporal Fusion in Driving Scenes. arXiv preprint arXiv:2302.05916","author":"Wen Qiang","year":"2023","unstructured":"Qiang Wen, Yue Wu, and Qifeng Chen. 2023. Video Waterdrop Removal via Spatio-Temporal Fusion in Driving Scenes. arXiv preprint arXiv:2302.05916 (2023)."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01041"},{"key":"e_1_3_2_1_67_1","volume-title":"European Conference on Computer Vision.","author":"Wu Hongtao","year":"2024","unstructured":"Hongtao Wu, Yijun Yang, Angelica Aviles-Rivero, Jingjing Ren, Sixiang chen, Haoyu Chen, and Lei Zhu. 2024. Semi-Supervised Video Desnowing Network via Temporal Decoupling Experts and Distribution-Driven Contrastive Regularization. In European Conference on Computer Vision."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612001"},{"key":"e_1_3_2_1_69_1","volume-title":"Segmamba: Long-range sequential modeling mamba for 3d medical image segmentation. arXiv preprint arXiv:2401.13560","author":"Xing Zhaohu","year":"2024","unstructured":"Zhaohu Xing, Tian Ye, Yijun Yang, Guang Liu, and Lei Zhu. 2024. Segmamba: Long-range sequential modeling mamba for 3d medical image segmentation. arXiv preprint arXiv:2401.13560 (2024)."},{"key":"e_1_3_2_1_70_1","unstructured":"Huihui Xu Yijun Yang Angelica I. Avil\u00e9s-Rivero Guang Yang Jing Qin and Lei Zhu. 2024. LGRNet: Local-Global Reciprocal Network for Uterine Fibroid Segmentation in Ultrasound Videos. https:\/\/api.semanticscholar.org\/CorpusID:271050719"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01179"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00176"},{"key":"e_1_3_2_1_73_1","first-page":"8569","article-title":"Recurrent multi-frame deraining: Combining physics guidance and adversarial learning","volume":"44","author":"Yang Wenhan","year":"2021","unstructured":"Wenhan Yang, Robby T Tan, Jiashi Feng, Shiqi Wang, Bin Cheng, and Jiaying Liu. 2021. Recurrent multi-frame deraining: Combining physics guidance and adversarial learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44, 11 (2021), 8569--8586.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00179"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01214"},{"key":"e_1_3_2_1_76_1","volume-title":"MammoDG: Generalisable Deep Learning Breaks the Limits of Cross-Domain Multi-Center Breast Cancer Screening. arXiv preprint arXiv:2308.01057","author":"Yang Yijun","year":"2023","unstructured":"Yijun Yang, Shujun Wang, Lihao Liu, Sarah Hickman, Fiona J Gilbert, Carola-Bibiane Sch\u00f6nlieb, and Angelica I Aviles-Rivero. 2023. MammoDG: Generalisable Deep Learning Breaks the Limits of Cross-Domain Multi-Center Breast Cancer Screening. arXiv preprint arXiv:2308.01057 (2023)."},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02419"},{"key":"e_1_3_2_1_78_1","volume-title":"Vivim: a video vision mamba for medical video object segmentation. arXiv preprint arXiv:2401.14168","author":"Yang Yijun","year":"2024","unstructured":"Yijun Yang, Zhaohu Xing, and Lei Zhu. 2024. Vivim: a video vision mamba for medical video object segmentation. arXiv preprint arXiv:2401.14168 (2024)."},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611742"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00573"},{"key":"e_1_3_2_1_81_1","volume-title":"Adherent raindrop modeling, detection and removal in video","author":"You Shaodi","year":"2015","unstructured":"Shaodi You, Robby T Tan, Rei Kawakami, Yasuhiro Mukaigawa, and Katsushi Ikeuchi. 2015. Adherent raindrop modeling, detection and removal in video. IEEE transactions on pattern analysis and machine intelligence, Vol. 38, 9 (2015), 1721--1733."},{"key":"e_1_3_2_1_82_1","volume-title":"Auformer: Vision transformers are parameter-efficient facial action unit detectors. arXiv preprint arXiv:2403.04697","author":"Yuan Kaishen","year":"2024","unstructured":"Kaishen Yuan, Zitong Yu, Xin Liu, Weicheng Xie, Huanjing Yue, and Jingyu Yang. 2024. Auformer: Vision transformers are parameter-efficient facial action unit detectors. arXiv preprint arXiv:2403.04697 (2024)."},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00070"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00564"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01458"},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3108019"},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148707"},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01539"},{"key":"e_1_3_2_1_90_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 '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680916","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680916","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:34Z","timestamp":1750295854000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680916"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":90,"alternative-id":["10.1145\/3664647.3680916","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680916","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}