{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T23:51:10Z","timestamp":1783641070079,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":52,"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":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12171072"],"award-info":[{"award-number":["12171072"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Natural Science Foundation of China","award":["12271083"],"award-info":[{"award-number":["12271083"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680905","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"1235-1244","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["A Novel State Space Model with Local Enhancement and State Sharing for Image Fusion"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7532-2122","authenticated-orcid":false,"given":"Zihan","family":"Cao","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1259-8674","authenticated-orcid":false,"given":"Xiao","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3178-9772","authenticated-orcid":false,"given":"Liang-Jian","family":"Deng","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3106-1113","authenticated-orcid":false,"given":"Yu","family":"Zhong","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Yuxuan Cai Yizhuang Zhou Qi Han Jianjian Sun Xiangwen Kong Jun Li and Xiangyu Zhang. 2023. Reversible Column Networks. In ICLR."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102158"},{"key":"e_1_3_2_2_3_1","volume-title":"Neural Shr\u00f6dinger Bridge Matching for Pansharpening. arXiv preprint arXiv:2404.11416","author":"Cao Zihan","year":"2024","unstructured":"Zihan Cao, Xiao Wu, and Liang-Jian Deng. 2024. Neural Shr\u00f6dinger Bridge Matching for Pansharpening. arXiv preprint arXiv:2404.11416 (2024)."},{"key":"e_1_3_2_2_4_1","volume-title":"Simple baselines for image restoration","author":"Chen Liangyu","unstructured":"Liangyu Chen, Xiaojie Chu, Xiangyu Zhang, and Jian Sun. 2022. Simple baselines for image restoration. In ECCV. Springer, 17--33."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3031366"},{"key":"e_1_3_2_2_6_1","first-page":"279","article-title":"Machine Learning in Pansharpening: A benchmark, from shallow to deep networks. IEEE Geosci","volume":"10","author":"Vivone Gemine","year":"2022","unstructured":"Liang-jian Deng, Gemine Vivone, Mercedes E. Paoletti, Giuseppe Scarpa, Jiang He, Yongjun Zhang, Jocelyn Chanussot, and Antonio Plaza. 2022. Machine Learning in Pansharpening: A benchmark, from shallow to deep networks. IEEE Geosci. Remote Sens. Mag., Vol. 10, 3 (2022), 279--315.","journal-title":"Remote Sens. Mag."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2023.3244750","article-title":"PSRT: Pyramid shuffle-and-reshuffle transformer for multispectral and hyperspectral image fusion","volume":"61","author":"Deng Shang-Qi","year":"2023","unstructured":"Shang-Qi Deng, Liang-Jian Deng, Xiao Wu, Ran Ran, Danfeng Hong, and Gemine Vivone. 2023. PSRT: Pyramid shuffle-and-reshuffle transformer for multispectral and hyperspectral image fusion. IEEE Trans. Geosci. Remote Sens., Vol. 61 (2023), 1--15.","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2916734"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2885616"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3078058"},{"key":"e_1_3_2_2_11_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly Jakob Uszkoreit and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In ICLR."},{"key":"e_1_3_2_2_12_1","first-page":"1","article-title":"MIMO-SST: Multi-Input Multi-Output Spatial-Spectral Transformer for Hyperspectral and Multispectral Image Fusion","volume":"62","author":"Fang Jian","year":"2024","unstructured":"Jian Fang, Jingxiang Yang, Abdolraheem Khader, and Liang Xiao. 2024. MIMO-SST: Multi-Input Multi-Output Spatial-Spectral Transformer for Hyperspectral and Multispectral Image Fusion. IEEE Trans. Geosci. Remote Sens., Vol. 62 (2024), 1--20.","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"e_1_3_2_2_13_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_2_14_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_2_15_1","unstructured":"Dongchen Han Xuran Pan Yizeng Han Shiji Song and Gao Huang. 2023. Flatten transformer: Vision transformer using focused linear attention. In CVPR. 5961--5971."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2898574"},{"key":"e_1_3_2_2_17_1","volume-title":"Pan-Mamba: Effective pan-sharpening with State Space Model. arXiv preprint arXiv:2402.12192","author":"He Xuanhua","year":"2024","unstructured":"Xuanhua He, Ke Cao, Keyu Yan, Rui Li, Chengjun Xie, Jie Zhang, and Man Zhou. 2024. Pan-Mamba: Effective pan-sharpening with State Space Model. arXiv preprint arXiv:2402.12192 (2024)."},{"key":"e_1_3_2_2_18_1","first-page":"1","article-title":"Fusformer: A transformer-based fusion network for hyperspectral image super-resolution","volume":"19","author":"Hu Jin-Fan","year":"2022","unstructured":"Jin-Fan Hu, Ting-Zhu Huang, Liang-Jian Deng, Hong-Xia Dou, Danfeng Hong, and Gemine Vivone. 2022. Fusformer: A transformer-based fusion network for hyperspectral image super-resolution. IEEE Geoscience and Remote Sensing Letters, Vol. 19 (2022), 1--5.","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084682"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2022.3152700"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19996"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2836307"},{"key":"e_1_3_2_2_23_1","volume-title":"Fourier-enhanced Implicit Neural Fusion Network for Multispectral and Hyperspectral Image Fusion. arXiv preprint arXiv:2404.15174","author":"Liang Yu-Jie","year":"2024","unstructured":"Yu-Jie Liang, Zihan Cao, Liang-Jian Deng, and Xiao Wu. 2024. Fourier-enhanced Implicit Neural Fusion Network for Multispectral and Hyperspectral Image Fusion. arXiv preprint arXiv:2404.15174 (2024)."},{"key":"e_1_3_2_2_24_1","volume-title":"Swin-umamba: Mamba-based unet with imagenet-based pretraining. arXiv preprint arXiv:2402.03302","author":"Liu Jiarun","year":"2024","unstructured":"Jiarun Liu, Hao Yang, Hong-Yu Zhou, Yan Xi, Lequan Yu, Yizhou Yu, Yong Liang, Guangming Shi, Shaoting Zhang, Hairong Zheng, et al. 2024. Swin-umamba: Mamba-based unet with imagenet-based pretraining. arXiv preprint arXiv:2402.03302 (2024)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.07.010"},{"key":"e_1_3_2_2_26_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_2_27_1","doi-asserted-by":"crossref","unstructured":"Ze Liu Yutong Lin Yue Cao Han Hu Yixuan Wei Zheng Zhang Stephen Lin and Baining Guo. 2021. Swin transformer: Hierarchical vision transformer using shifted windows. In ICCV. 10012--10022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2017.2761021"},{"key":"e_1_3_2_2_29_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_2_30_1","volume-title":"Satinder Singh, and Feryal M. P. Behbahani.","author":"Lu Chris Xiaoxuan","year":"2023","unstructured":"Chris Xiaoxuan Lu, Yannick Schroecker, Albert Gu, Emilio Parisotto, Jakob Nicolaus Foerster, Satinder Singh, and Feryal M. P. Behbahani. 2023. Structured State Space Models for In-Context Reinforcement Learning. ArXiv, Vol. abs\/2303.03982 (2023)."},{"key":"e_1_3_2_2_31_1","volume-title":"U-mamba: Enhancing long-range dependency for biomedical image segmentation. arXiv preprint arXiv:2401.04722","author":"Ma Jun","year":"2024","unstructured":"Jun Ma, Feifei Li, and Bo Wang. 2024. U-mamba: Enhancing long-range dependency for biomedical image segmentation. arXiv preprint arXiv:2401.04722 (2024)."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101907"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2023.3279864","article-title":"PanDiff: A Novel Pansharpening Method Based on Denoising Diffusion Probabilistic Model","volume":"61","author":"Meng Qingyan","year":"2023","unstructured":"Qingyan Meng, Wenxu Shi, Sijia Li, and Linlin Zhang. 2023. PanDiff: A Novel Pansharpening Method Based on Denoising Diffusion Probabilistic Model. IEEE Trans. Geosci. Remote Sens., Vol. 61 (2023), 1--17.","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"e_1_3_2_2_34_1","first-page":"2846","article-title":"S4nd: Modeling images and videos as multidimensional signals with state spaces","volume":"35","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. Neurips, Vol. 35 (2022), 2846--2861.","journal-title":"Neurips"},{"key":"e_1_3_2_2_35_1","volume-title":"U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention (MICCAI)","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention (MICCAI). Springer, 234--241."},{"key":"e_1_3_2_2_36_1","volume-title":"U-net: Convolutional networks for biomedical image segmentation","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In MICCAI. Springer, 234--241."},{"key":"e_1_3_2_2_37_1","volume-title":"Vm-unet: Vision mamba unet for medical image segmentation. arXiv preprint arXiv:2402.02491","author":"Ruan Jiacheng","year":"2024","unstructured":"Jiacheng Ruan and Suncheng Xiang. 2024. Vm-unet: Vision mamba unet for medical image segmentation. arXiv preprint arXiv:2402.02491 (2024)."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3319512"},{"key":"e_1_3_2_2_39_1","volume-title":"Interpretable Model-Driven Deep Network for Hyperspectral, Multispectral, and Panchromatic Image Fusion","author":"Tian Xin","year":"2023","unstructured":"Xin Tian, Kun Li, Wei Zhang, Zhongyuan Wang, and Jiayi Ma. 2023. Interpretable Model-Driven Deep Network for Hyperspectral, Multispectral, and Panchromatic Image Fusion. IEEE Trans. Neural Netw. Learn. Syst. (2023), 1--14."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.08.032"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2819501"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"crossref","unstructured":"Wenhai Wang Enze Xie Xiang Li Deng-Ping Fan Kaitao Song Ding Liang Tong Lu Ping Luo and Ling Shao. 2021. Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In ICCV. 568--578.","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_2_2_44_1","unstructured":"Xiao Wu Ting-Zhu Huang Liang-Jian Deng and Tian-Jing Zhang. 2021. Dynamic cross feature fusion for remote sensing pansharpening. In ICCV. 14687--14696."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3247165"},{"key":"e_1_3_2_2_46_1","first-page":"1","article-title":"An Iterative Regularization Method Based on Tensor Subspace Representation for Hyperspectral Image Super-Resolution","volume":"60","author":"Xu Ting","year":"2022","unstructured":"Ting Xu, Ting-Zhu Huang, Liang-Jian Deng, and Naoto Yokoya. 2022. An Iterative Regularization Method Based on Tensor Subspace Representation for Hyperspectral Image Super-Resolution. IEEE Trans. Geosci. Remote Sens., Vol. 60 (2022), 1--16.","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"crossref","unstructured":"Junfeng Yang Xueyang Fu Yuwen Hu Yue Huang Xinghao Ding and John Paisley. 2017. PanNet: A Deep Network Architecture for Pan-Sharpening. In ICCV. 1753--1761.","DOI":"10.1109\/ICCV.2017.193"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3018732"},{"key":"e_1_3_2_2_50_1","first-page":"1","article-title":"Effective Pan-Sharpening With Transformer and Invertible Neural Network","volume":"60","author":"Zhou Man","year":"2022","unstructured":"Man Zhou, Xueyang Fu, Jie Huang, Feng Zhao, Aiping Liu, and Rujing Wang. 2022. Effective Pan-Sharpening With Transformer and Invertible Neural Network. IEEE Trans. Geosci. Remote Sens., Vol. 60 (2022), 1--15.","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"crossref","unstructured":"Man Zhou Jie Huang Yanchi Fang Xueyang Fu and Aiping Liu. 2022. Pan-sharpening with Customized Transformer and Invertible Neural Network. In AAAI.","DOI":"10.1609\/aaai.v36i3.20267"},{"key":"e_1_3_2_2_52_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\/3664647.3680905","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680905","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:33Z","timestamp":1750295853000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680905"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":52,"alternative-id":["10.1145\/3664647.3680905","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680905","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"}}]}}