{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T03:06:17Z","timestamp":1783825577353,"version":"3.55.0"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T00:00:00Z","timestamp":1753315200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T00:00:00Z","timestamp":1753315200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62127813"],"award-info":[{"award-number":["62127813"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1007\/s11760-025-04549-y","type":"journal-article","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T14:45:09Z","timestamp":1753368309000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["LGMFuse: A Multi-modal Image Fusion Method Based on Local and Global Mamba"],"prefix":"10.1007","volume":"19","author":[{"given":"Xuedong","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meiling","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jialin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,24]]},"reference":[{"issue":"20","key":"4549_CR1","doi-asserted-by":"publisher","first-page":"31283","DOI":"10.1364\/OE.434398","volume":"29","author":"H Wang","year":"2021","unstructured":"Wang, H., Hu, H., Jiang, J., Li, X., Zhang, W., Cheng, Z., Liu, T.: Automatic underwater polarization imaging without background region or any prior. Opt. Express 29(20), 31283\u201331295 (2021)","journal-title":"Opt. Express"},{"key":"4549_CR2","doi-asserted-by":"crossref","unstructured":"Kalra, A., Taamazyan, V., Rao, S.K., Venkataraman, K., Raskar, R., Kadambi, A.: Deep polarization cues for transparent object segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8602\u20138611 (2020)","DOI":"10.1109\/CVPR42600.2020.00863"},{"issue":"5","key":"4549_CR3","doi-asserted-by":"publisher","first-page":"3199","DOI":"10.1007\/s00371-023-03022-6","volume":"40","author":"A Tan","year":"2024","unstructured":"Tan, A., Guo, T., Zhao, Y., Wang, Y., Li, X.: Object detection based on polarization image fusion and grouped convolutional attention network. Vis. Comput. 40(5), 3199\u20133215 (2024)","journal-title":"Vis. Comput."},{"key":"4549_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.110245","volume":"146","author":"X Wang","year":"2025","unstructured":"Wang, X., Xu, J., Ding, J.: Polarization-based camouflaged object detection with high-resolution adaptive fusion network. Eng. Appl. Artif. Intell. 146, 110245 (2025)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"4549_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.optlaseng.2024.108712","volume":"185","author":"J Duan","year":"2025","unstructured":"Duan, J., Gao, M., Zhao, G., Liu, J., Zhang, Z., He, X.: Dstokes-cgcp: A low-light color polarization image enhancement method combining chroma spectrum and global contour awareness. Opt. Lasers Eng. 185, 108712 (2025)","journal-title":"Opt. Lasers Eng."},{"key":"4549_CR6","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhou, P., Zhou, G., Wang, H., Lu, Y., Peng, Y.: A comprehensive survey of visible and infrared imaging in complex environments: Principle, degradation and enhancement. Information Fusion, 103036 (2025)","DOI":"10.1016\/j.inffus.2025.103036"},{"key":"4549_CR7","doi-asserted-by":"crossref","unstructured":"Liu, Q., Liu, R., Zheng, B., Wang, H., Fu, Y.: Infrared small target detection with scale and location sensitivity. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 17490\u201317499 (2024)","DOI":"10.1109\/CVPR52733.2024.01656"},{"key":"4549_CR8","doi-asserted-by":"crossref","unstructured":"Zhang, M., Wang, Y., Guo, J., Li, Y., Gao, X., Zhang, J.: Irsam: Advancing segment anything model for infrared small target detection. In: European Conference on Computer Vision, pp. 233\u2013249 (2024). Springer","DOI":"10.1007\/978-3-031-72855-6_14"},{"key":"4549_CR9","volume-title":"Advances in Neural Information Processing Systems","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N.: Kaiser, L.u., Polosukhin, I.: Attention is all you need. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 30. Curran Associates Inc, New York (2017)"},{"key":"4549_CR10","unstructured":"Lu, J., Yao, J., Zhang, J., Zhu, X., Xu, H., Gao, W., XU, C., Xiang, T., Zhang, L.: Soft: Softmax-free transformer with linear complexity. In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P.S., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems, vol. 34, pp. 21297\u201321309. Curran Associates, Inc., New York (2021)"},{"key":"4549_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.113539","volume":"318","author":"P Shi","year":"2025","unstructured":"Shi, P., Dong, X., Ge, R., Liu, Z., Yang, A.: Dp-m3d: Monocular 3d object detection algorithm with depth perception capability. Knowl.-Based Syst. 318, 113539 (2025)","journal-title":"Knowl.-Based Syst."},{"issue":"1","key":"4549_CR12","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.1177\/03611981241258753","volume":"2679","author":"X Dong","year":"2025","unstructured":"Dong, X., Shi, P., Liang, T., Yang, A.: Ctaffnet: Cnn-transformer adaptive feature fusion object detection algorithm for complex traffic scenarios. Transp. Res. Rec. 2679(1), 1947\u20131965 (2025)","journal-title":"Transp. Res. Rec."},{"key":"4549_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2024.102814","volume":"84","author":"X Dong","year":"2024","unstructured":"Dong, X., Shi, P., Qi, H., Yang, A., Liang, T.: Ts-bev: Bev object detection algorithm based on temporal-spatial feature fusion. Displays 84, 102814 (2024)","journal-title":"Displays"},{"key":"4549_CR14","unstructured":"Gu, A., Goel, K., R\u00e9, C.: Efficiently modeling long sequences with structured state spaces. Preprint at https:\/\/arxiv.org\/abs\/2111.00396 (2021)"},{"key":"4549_CR15","unstructured":"Gu, A., Dao, T.: Mamba: Linear-Time Sequence Modeling with Selective State Spaces. Preprint at https:\/\/arxiv.org\/abs\/2312.00752 (2024)"},{"key":"4549_CR16","unstructured":"Shi, Y., Dong, M., Xu, C.: Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model. Preprint at https:\/\/arxiv.org\/abs\/2405.14174 (2024)"},{"key":"4549_CR17","doi-asserted-by":"crossref","unstructured":"Shi, Y., Xia, B., Jin, X., Wang, X., Zhao, T., Xia, X., Xiao, X., Yang, W.: Vmambair: Visual state space model for image restoration. IEEE Transactions on Circuits and Systems for Video Technology (2025)","DOI":"10.1109\/TCSVT.2025.3530090"},{"key":"4549_CR18","doi-asserted-by":"crossref","unstructured":"Wang, D., Liu, J., Fan, X., Liu, R.: Unsupervised Misaligned Infrared and Visible Image Fusion via Cross-Modality Image Generation and Registration. Preprint at https:\/\/arxiv.org\/abs\/2205.11876 (2022)","DOI":"10.24963\/ijcai.2022\/487"},{"key":"4549_CR19","doi-asserted-by":"publisher","first-page":"5413","DOI":"10.1109\/TMM.2022.3192661","volume":"25","author":"W Tang","year":"2022","unstructured":"Tang, W., He, F., Liu, Y.: Ydtr: Infrared and visible image fusion via y-shape dynamic transformer. IEEE Trans. Multimedia 25, 5413\u20135428 (2022)","journal-title":"IEEE Trans. Multimedia"},{"issue":"12","key":"4549_CR20","doi-asserted-by":"publisher","first-page":"2121","DOI":"10.1109\/JAS.2022.106082","volume":"9","author":"L Tang","year":"2022","unstructured":"Tang, L., Deng, Y., Ma, Y., Huang, J., Ma, J.: Superfusion: A versatile image registration and fusion network with semantic awareness. IEEE\/CAA Journal of Automatica Sinica 9(12), 2121\u20132137 (2022)","journal-title":"IEEE\/CAA Journal of Automatica Sinica"},{"key":"4549_CR21","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Bai, H., Zhang, J., Zhang, Y., Zhang, K., Xu, S., Chen, D., Timofte, R., Van\u00a0Gool, L.: Equivariant multi-modality image fusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 25912\u201325921 (2024)","DOI":"10.1109\/CVPR52733.2024.02448"},{"key":"4549_CR22","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.inffus.2021.12.004","volume":"82","author":"L Tang","year":"2022","unstructured":"Tang, L., Yuan, J., Ma, J.: Image fusion in the loop of high-level vision tasks: A semantic-aware real-time infrared and visible image fusion network. Information Fusion 82, 28\u201342 (2022)","journal-title":"Information Fusion"},{"key":"4549_CR23","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Bai, H., Zhang, J., Zhang, Y., Xu, S., Lin, Z., Timofte, R., Van\u00a0Gool, L.: Cddfuse: Correlation-driven dual-branch feature decomposition for multi-modality image fusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5906\u20135916 (2023)","DOI":"10.1109\/CVPR52729.2023.00572"},{"key":"4549_CR24","doi-asserted-by":"crossref","unstructured":"Rao, D., Xu, T., Wu, X.-J.: Tgfuse: An infrared and visible image fusion approach based on transformer and generative adversarial network. IEEE Transactions on Image Processing (2023)","DOI":"10.1109\/TIP.2023.3273451"},{"key":"4549_CR25","doi-asserted-by":"crossref","unstructured":"Wang, D., Liu, J., Ma, L., Liu, R., Fan, X.: Improving misaligned multi-modality image fusion with one-stage progressive dense registration. IEEE Transactions on Circuits and Systems for Video Technology (2024)","DOI":"10.1109\/TCSVT.2024.3412743"},{"key":"4549_CR26","doi-asserted-by":"crossref","unstructured":"Wang, Z., Chen, Y., Shao, W., Li, H., Zhang, L.: Swinfuse: A residual swin transformer fusion network for infrared and visible images. IEEE Trans. Instrum. Meas. 71, 1\u201312 (2022)","DOI":"10.1109\/TIM.2022.3191664"},{"key":"4549_CR27","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., Wang, X.: Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model. Preprint at https:\/\/arxiv.org\/abs\/2401.09417 (2024)"},{"key":"4549_CR28","first-page":"103031","volume-title":"Advances in Neural Information Processing Systems","author":"Y Liu","year":"2024","unstructured":"Liu, Y., Tian, Y., Zhao, Y., Yu, H., Xie, L., Wang, Y., Ye, Q., Jiao, J., Liu, Y.: Vmamba: Visual state space model. In: Globerson, A., Mackey, L., Belgrave, D., Fan, A., Paquet, U., Tomczak, J., Zhang, C. (eds.) Advances in Neural Information Processing Systems, vol. 37, pp. 103031\u2013103063. Curran Associates Inc, New York (2024)"},{"issue":"1","key":"4549_CR29","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1007\/s44267-024-00072-9","volume":"2","author":"X Xie","year":"2024","unstructured":"Xie, X., Cui, Y., Tan, T., Zheng, X., Yu, Z.: Fusionmamba: Dynamic feature enhancement for multimodal image fusion with mamba. Visual Intelligence 2(1), 37 (2024)","journal-title":"Visual Intelligence"},{"key":"4549_CR30","doi-asserted-by":"crossref","unstructured":"Huang, T., Pei, X., You, S., Wang, F., Qian, C., Xu, C.: LocalMamba: Visual State Space Model with Windowed Selective Scan. Preprint at https:\/\/arxiv.org\/abs\/2403.09338 (2024)","DOI":"10.1007\/978-3-031-91979-4_2"},{"key":"4549_CR31","first-page":"12077","volume-title":"Advances in Neural Information Processing Systems","author":"E Xie","year":"2021","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: Segformer: Simple and efficient design for semantic segmentation with transformers. In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P.S., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems, vol. 34, pp. 12077\u201312090. Curran Associates Inc, New York (2021)"},{"key":"4549_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.optlaseng.2024.108159","volume":"178","author":"J Duan","year":"2024","unstructured":"Duan, J., Song, J., Zhu, Y., Zhang, H., Liu, J., Zheng, Y.: Polarization image fusion method based on polarization saliency with generator adversarial network. Opt. Lasers Eng. 178, 108159 (2024)","journal-title":"Opt. Lasers Eng."},{"key":"4549_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.optlaseng.2024.108176","volume":"178","author":"J Duan","year":"2024","unstructured":"Duan, J., Liu, J., Hao, Y., Chen, G., Zheng, Y., Jia, L.: Joint target geometry and polarization properties for polarization image fusion. Opt. Lasers Eng. 178, 108176 (2024)","journal-title":"Opt. Lasers Eng."},{"key":"4549_CR34","first-page":"1","volume":"62","author":"S Peng","year":"2024","unstructured":"Peng, S., Zhu, X., Deng, H., Deng, L.-J., Lei, Z.: Fusionmamba: Efficient remote sensing image fusion with state space model. IEEE Trans. Geosci. Remote Sens. 62, 1\u201316 (2024)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"4549_CR35","doi-asserted-by":"crossref","unstructured":"Liu, J., Fan, X., Huang, Z., Wu, G., Liu, R., Zhong, W., Luo, Z.: Target-aware dual adversarial learning and a multi-scenario multi-modality benchmark to fuse infrared and visible for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5802\u20135811 (2022)","DOI":"10.1109\/CVPR52688.2022.00571"},{"key":"4549_CR36","doi-asserted-by":"publisher","unstructured":"Toet, A.: TNO Image Fusion Dataset. figshare. figshare https:\/\/doi.org\/10.6084\/m9.figshare.1008029.v1 (2014)","DOI":"10.6084\/m9.figshare.1008029.v1"},{"key":"4549_CR37","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107303","volume":"127","author":"X Wang","year":"2024","unstructured":"Wang, X., Ding, J., Zhang, Z., Xu, J., Gao, J.: Ipnet: Polarization-based camouflaged object detection via dual-flow network. Eng. Appl. Artif. Intell. 127, 107303 (2024)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"4549_CR38","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: Exceeding yolo series in 2021. Preprint at https:\/\/arxiv.org\/abs\/2107.08430 (2021)"},{"key":"4549_CR39","doi-asserted-by":"publisher","DOI":"10.1016\/j.optlastec.2024.111666","volume":"181","author":"Y Sun","year":"2025","unstructured":"Sun, Y., Dong, M., Yu, M., Zhu, L.: Mbhfuse: A multi-branch heterogeneous global and local infrared and visible image fusion with differential convolutional amplification features. Optics & Laser Technology 181, 111666 (2025)","journal-title":"Optics & Laser Technology"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04549-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-025-04549-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04549-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T21:56:15Z","timestamp":1757282175000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-025-04549-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,24]]},"references-count":39,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["4549"],"URL":"https:\/\/doi.org\/10.1007\/s11760-025-04549-y","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-6331691\/v1","asserted-by":"object"}]},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,24]]},"assertion":[{"value":"29 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 June 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 July 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"All authors approved the final manuscript and the submission to this journal.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}],"article-number":"908"}}