{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T21:18:11Z","timestamp":1778620691099,"version":"3.51.4"},"reference-count":48,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers & Geosciences"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.cageo.2026.106169","type":"journal-article","created":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T07:30:42Z","timestamp":1775633442000},"page":"106169","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Synergistic Mamba-Transformer fusion for high-fidelity land cover classification from multi-modal remote sensing imagery"],"prefix":"10.1016","volume":"213","author":[{"given":"Zhongqin","family":"Bi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weina","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.cageo.2026.106169_b1","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.isprsjprs.2017.11.011","article-title":"Beyond RGB: Very high resolution urban remote sensing with multimodal deep networks","volume":"140","author":"Audebert","year":"2018","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.cageo.2026.106169_b2","series-title":"Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.","first-page":"1785","article-title":"Remote sensing semantic segmentation based on multimodal feature alignment and fusion","volume":"XLVIII-G-2025","author":"Chang","year":"2025"},{"key":"10.1016\/j.cageo.2026.106169_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.131555","article-title":"Efficient semantic segmentation of remote sensing images through dynamic feature enhancement and multimodal alignment fusion","volume":"657","author":"Chen","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.cageo.2026.106169_b4","article-title":"What is a good evaluation measure for semantic segmentation?","volume":"26","author":"Csurka","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cageo.2026.106169_b5","doi-asserted-by":"crossref","first-page":"1585","DOI":"10.1109\/JPROC.2015.2462751","article-title":"Challenges and opportunities of multimodality and data fusion in remote sensing","volume":"103","author":"Dalla Mura","year":"2015","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.cageo.2026.106169_b6","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.isprsjprs.2020.01.013","article-title":"ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data","volume":"162","author":"Diakogiannis","year":"2020","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.cageo.2026.106169_b7","unstructured":"Dosovitskiy, A., et al., 2021. An image is worth 16x16 words: Transformers for image recognition at scale. In: Proc. Int. Conf. Learn. Represent. pp. 1\u201322."},{"key":"10.1016\/j.cageo.2026.106169_b8","first-page":"1","article-title":"MSFMamba: Multiscale feature fusion state space model for multisource remote sensing image classification","volume":"63","author":"Gao","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.cageo.2026.106169_b9","doi-asserted-by":"crossref","first-page":"10990","DOI":"10.1109\/JSTARS.2021.3119654","article-title":"STransFuse: Fusing swin transformer and convolutional neural network for remote sensing image semantic segmentation","volume":"14","author":"Gao","year":"2021","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens."},{"key":"10.1016\/j.cageo.2026.106169_b10","doi-asserted-by":"crossref","first-page":"1560","DOI":"10.1109\/JPROC.2015.2449668","article-title":"Multimodal classification of remote sensing images: A review and future directions","volume":"103","author":"G\u00f3mez-Chova","year":"2015","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.cageo.2026.106169_b11","series-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023"},{"key":"10.1016\/j.cageo.2026.106169_b12","doi-asserted-by":"crossref","DOI":"10.1007\/s11432-020-3084-1","article-title":"Multimodal hyperspectral remote sensing: An overview and perspective","volume":"64","author":"Gu","year":"2021","journal-title":"Sci. China Inf. Sci."},{"key":"10.1016\/j.cageo.2026.106169_b13","series-title":"MambaVision: A hybrid mamba-transformer vision backbone","author":"Hatamizadeh","year":"2024"},{"key":"10.1016\/j.cageo.2026.106169_b14","first-page":"1","article-title":"Swin transformer embedding unet for remote sensing image semantic segmentation","volume":"60","author":"He","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.cageo.2026.106169_b15","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.isprsjprs.2021.12.007","article-title":"CMGFNet: A deep cross-modal gated fusion network for building extraction from very high-resolution remote sensing images","volume":"184","author":"Hosseinpour","year":"2022","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.cageo.2026.106169_b16","doi-asserted-by":"crossref","first-page":"1449","DOI":"10.1109\/JPROC.2015.2460697","article-title":"Multimodal data fusion: An overview of methods, challenges, and prospects","volume":"103","author":"Lahat","year":"2015","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.cageo.2026.106169_b17","article-title":"Deep learning in multimodal remote sensing data fusion: A comprehensive review","volume":"112","author":"Li","year":"2022","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"10.1016\/j.cageo.2026.106169_b18","first-page":"1","article-title":"Position-aware differential denoising transformer for semantic segmentation of remote sensing images","volume":"23","author":"Li","year":"2026","journal-title":"IEEE Geosci. Remote. Sens. Lett."},{"key":"10.1016\/j.cageo.2026.106169_b19","first-page":"1","article-title":"A euclidean affinity-augmented hyperbolic neural network for semantic segmentation of remote sensing images","volume":"63","author":"Li","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.cageo.2026.106169_b20","first-page":"1","article-title":"Semantic segmentation of remote sensing images by interactive representation refinement and geometric prior-guided inference","volume":"62","author":"Li","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.cageo.2026.106169_b21","first-page":"1","article-title":"Frequency-guided denoising network for semantic segmentation of remote sensing images","volume":"64","author":"Li","year":"2026","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.cageo.2026.106169_b22","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.isprsjprs.2021.09.005","article-title":"ABCNet: Attentive bilateral contextual network for efficient semantic segmentation of fine-resolution remotely sensed imagery","volume":"181","author":"Li","year":"2021","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.cageo.2026.106169_b23","series-title":"Vision mamba: A comprehensive survey and taxonomy","author":"Liu","year":"2024"},{"key":"10.1016\/j.cageo.2026.106169_b24","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al., 2021. Swin transformer: Hierarchical vision transformer using shifted windows. In: Proc. IEEE\/CVF Int. Conf. Comput. Vis.. ICCV, pp. 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10.1016\/j.cageo.2026.106169_b25","article-title":"A transformer-based multi-modal fusion network for semantic segmentation of high-resolution remote sensing imagery","volume":"133","author":"Liu","year":"2024","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"10.1016\/j.cageo.2026.106169_b26","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T., 2015. Fully convolutional networks for semantic segmentation. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit.. CVPR, pp. 3431\u20133440.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"10.1016\/j.cageo.2026.106169_b27","first-page":"1","article-title":"SAM-assisted remote sensing imagery semantic segmentation with object and boundary constraints","volume":"62","author":"Ma","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.cageo.2026.106169_b28","doi-asserted-by":"crossref","first-page":"20116","DOI":"10.1109\/JSTARS.2024.3486906","article-title":"Adjacent-scale multimodal fusion networks for semantic segmentation of remote sensing data","volume":"17","author":"Ma","year":"2024","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens."},{"key":"10.1016\/j.cageo.2026.106169_b29","doi-asserted-by":"crossref","first-page":"3463","DOI":"10.1109\/JSTARS.2022.3165005","article-title":"A crossmodal multiscale fusion network for semantic segmentation of remote sensing data","volume":"15","author":"Ma","year":"2022","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens."},{"key":"10.1016\/j.cageo.2026.106169_b30","first-page":"1","article-title":"RS3Mamba: Visual state space model for remote sensing image semantic segmentation","volume":"21","author":"Ma","year":"2024","journal-title":"IEEE Geosci. Remote. Sens. Lett."},{"key":"10.1016\/j.cageo.2026.106169_b31","first-page":"1","article-title":"A unified framework with multimodal fine-tuning for remote sensing semantic segmentation","volume":"63","author":"Ma","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.cageo.2026.106169_b32","article-title":"A multilevel multimodal fusion transformer for remote sensing semantic segmentation","volume":"62","author":"Ma","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.cageo.2026.106169_b33","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T., 2015. U-Net: Convolutional networks for biomedical image segmentation. In: Proc. Int. Conf. Med. Image Comput. Comput.-Assist. Intervent.. pp. 234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"10.1016\/j.cageo.2026.106169_b34","doi-asserted-by":"crossref","unstructured":"Spasev, V., Dimitrovski, I., Kitanovski, I., Chorbev, I., 2023. Semantic segmentation of remote sensing images definition, methods, datasets and applications. In: International Conference on ICT Innovations. pp. 127\u2013140.","DOI":"10.1007\/978-3-031-54321-0_9"},{"key":"10.1016\/j.cageo.2026.106169_b35","doi-asserted-by":"crossref","unstructured":"Wan, Z., Zhang, P., Wang, Y., Yong, S., Stepputtis, S., Sycara, K., Xie, Y., 2025. Sigma: Siamese mamba network for multi-modal semantic segmentation. In: Proc. IEEE\/CVF Winter Conference on Applications of Computer Vision. WACV, pp. 1734\u20131744.","DOI":"10.1109\/WACV61041.2025.00176"},{"key":"10.1016\/j.cageo.2026.106169_b36","doi-asserted-by":"crossref","first-page":"7266","DOI":"10.3390\/s24227266","article-title":"MFMamba: A mamba-based multi-modal fusion network for semantic segmentation of remote sensing images","volume":"24","author":"Wang","year":"2024","journal-title":"Sensors"},{"key":"10.1016\/j.cageo.2026.106169_b37","doi-asserted-by":"crossref","first-page":"3495","DOI":"10.3390\/s24113495","article-title":"Transformers for remote sensing: A systematic review and analysis","volume":"24","author":"Wang","year":"2024","journal-title":"Sensors"},{"key":"10.1016\/j.cageo.2026.106169_b38","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2023.3314641","article-title":"CMTFNet: CNN and multiscale transformer fusion network for remote sensing image semantic segmentation","volume":"61","author":"Wu","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.cageo.2026.106169_b39","article-title":"Remote sensing enables rapid assessment of the March 28, 2025 Myanmar earthquake","author":"Xu","year":"2025","journal-title":"Sci. Bull."},{"key":"10.1016\/j.cageo.2026.106169_b40","first-page":"1","article-title":"MambaTriNet: A mamba-based tribackbone multimodal remote sensing image semantic segmentation model","volume":"22","author":"Ye","year":"2025","journal-title":"IEEE Geosci. Remote. Sens. Lett."},{"key":"10.1016\/j.cageo.2026.106169_b41","doi-asserted-by":"crossref","first-page":"41180","DOI":"10.1109\/ACCESS.2024.3376441","article-title":"A comprehensive survey of convolutions in deep learning: Applications, challenges, and future trends","volume":"12","author":"Younesi","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.cageo.2026.106169_b42","first-page":"1","article-title":"Transformer and CNN hybrid deep neural network for semantic segmentation of very-high-resolution remote sensing imagery","volume":"60","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.cageo.2026.106169_b43","doi-asserted-by":"crossref","first-page":"14679","DOI":"10.1109\/TITS.2023.3300537","article-title":"CMX: Cross-modal fusion for RGB-x semantic segmentation with transformers","volume":"24","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.cageo.2026.106169_b44","article-title":"Comprehensive assessment of the recent dike breach at Dongting Lake","volume":"2","author":"Zhang","year":"2024","journal-title":"Innov. Geosci."},{"key":"10.1016\/j.cageo.2026.106169_b45","doi-asserted-by":"crossref","DOI":"10.1016\/j.rse.2023.113801","article-title":"Fully automatic training sample collection for detecting multi-decadal inland\/seaward urban sprawl","volume":"298","author":"Zhang","year":"2023","journal-title":"Remote Sens. Environ."},{"key":"10.1016\/j.cageo.2026.106169_b46","doi-asserted-by":"crossref","first-page":"5683","DOI":"10.3390\/app14135683","article-title":"A survey on visual mamba","volume":"14","author":"Zhang","year":"2024","journal-title":"Appl. Sci."},{"issue":"19","key":"10.1016\/j.cageo.2026.106169_b47","doi-asserted-by":"crossref","DOI":"10.1016\/j.heliyon.2024.e38495","article-title":"Samba: Semantic segmentation of remotely sensed images with state space model","volume":"10","author":"Zhu","year":"2024","journal-title":"Heliyon"},{"key":"10.1016\/j.cageo.2026.106169_b48","first-page":"1","article-title":"Unetmamba: An efficient UNet-like mamba for semantic segmentation of high-resolution remote sensing images","volume":"22","author":"Zhu","year":"2025","journal-title":"IEEE Geosci. Remote. Sens. Lett."}],"container-title":["Computers & Geosciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S009830042600066X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S009830042600066X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T20:34:45Z","timestamp":1778618085000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S009830042600066X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":48,"alternative-id":["S009830042600066X"],"URL":"https:\/\/doi.org\/10.1016\/j.cageo.2026.106169","relation":{},"ISSN":["0098-3004"],"issn-type":[{"value":"0098-3004","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Synergistic Mamba-Transformer fusion for high-fidelity land cover classification from multi-modal remote sensing imagery","name":"articletitle","label":"Article Title"},{"value":"Computers & Geosciences","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cageo.2026.106169","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"106169"}}