{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T14:20:02Z","timestamp":1778768402011,"version":"3.51.4"},"reference-count":52,"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"}],"funder":[{"DOI":"10.13039\/501100007310","name":"Wuyi University","doi-asserted-by":"publisher","award":["FKLBDAITI202403"],"award-info":[{"award-number":["FKLBDAITI202403"]}],"id":[{"id":"10.13039\/501100007310","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62406224"],"award-info":[{"award-number":["62406224"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62020106004"],"award-info":[{"award-number":["62020106004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.neucom.2026.133665","type":"journal-article","created":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T20:31:42Z","timestamp":1776285102000},"page":"133665","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["WAMNet: Wavelet-enhanced asymmetric mamba network for semantic segmentation of multimodal remote sensing images"],"prefix":"10.1016","volume":"685","author":[{"given":"Fei","family":"Wang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4547-4659","authenticated-orcid":false,"given":"Yanhong","family":"Yang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3009-5570","authenticated-orcid":false,"given":"Haozheng","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Chengkun","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7435-7267","authenticated-orcid":false,"given":"Chaoyang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yushan","family":"Xue","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6705-3831","authenticated-orcid":false,"given":"Shengyong","family":"Chen","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.133665_bib0005","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.neucom.2019.01.115","article-title":"GAN-based virtual-to-real image translation for urban scene semantic segmentation","volume":"394","author":"Guo","year":"2020","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133665_bib0010","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1016\/j.neucom.2022.07.086","article-title":"Road extraction from satellite images with iterative cross-task feature enhancement","volume":"506","author":"Yin","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133665_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.petrol.2021.109633","article-title":"UAV-based remote sensing for the petroleum industry and environmental monitoring: state-of-the-art and perspectives","volume":"208","author":"Asadzadeh","year":"2022","journal-title":"J. Pet. Sci. Eng."},{"key":"10.1016\/j.neucom.2026.133665_bib0020","doi-asserted-by":"crossref","first-page":"69445","DOI":"10.1109\/ACCESS.2024.3401416","article-title":"Land cover classification from RGB and NIR satellite images using modified U-Net model","volume":"12","author":"Baek","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.neucom.2026.133665_bib0025","article-title":"A dual-stream high resolution network: deep fusion of GF-2 and GF-3 data for land cover classification","volume":"112","author":"Ren","year":"2022","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"10.1016\/j.neucom.2026.133665_bib0030","first-page":"1","article-title":"Multimodal fusion transformer for remote sensing image classification","volume":"61","author":"Roy","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.neucom.2026.133665_bib0035","article-title":"DASFNet: dense-attention\u2013similarity-fusion network for scene classification of dual-modal remote-sensing images","volume":"115","author":"Jin","year":"2022","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"10.1016\/j.neucom.2026.133665_bib0040","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.neucom.2022.04.045","article-title":"Multi-source collaborative enhanced for remote sensing images semantic segmentation","volume":"493","author":"Zhao","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133665_bib0045","article-title":"A multimodal fusion framework for semantic segmentation of remote sensing based on multilevel feature fusion learning","author":"Liu","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133665_bib0050","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.neucom.2026.133665_bib0055","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133665_bib0060","doi-asserted-by":"crossref","first-page":"2543","DOI":"10.1109\/JSTARS.2023.3341628","article-title":"Improved yolov5s with coordinate attention for small and dense object detection from optical remote sensing images","volume":"17","author":"Wu","year":"2023","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"10.1016\/j.neucom.2026.133665_bib0065","author":"Gu"},{"key":"10.1016\/j.neucom.2026.133665_bib0070","series-title":"2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","first-page":"1734","article-title":"Sigma: siamese mamba network for multi-modal semantic segmentation","author":"Wan","year":"2025"},{"key":"10.1016\/j.neucom.2026.133665_bib0075","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103150","article-title":"MGF-GCN: multimodal interaction mamba-aided graph convolutional fusion network for semantic segmentation of remote sensing images","volume":"122","author":"Zhao","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.neucom.2026.133665_bib0080","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7608","article-title":"Asymformer: asymmetrical cross-modal representation learning for mobile platform real-time RGB-d semantic segmentation","author":"Du","year":"2024"},{"key":"10.1016\/j.neucom.2026.133665_bib0085","doi-asserted-by":"crossref","first-page":"231","DOI":"10.5194\/isprsarchives-XL-3-231-2014","article-title":"Photogrammetric DSM denoising","volume":"40","author":"Nex","year":"2014","journal-title":"Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"10.1016\/j.neucom.2026.133665_bib0090","series-title":"Asian Conference on Computer Vision","first-page":"213","article-title":"FuseNet: incorporating depth into semantic segmentation via fusion-based CNN architecture","author":"Hazirbas","year":"2016"},{"key":"10.1016\/j.neucom.2026.133665_bib0095","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.neucom.2026.133665_bib0100","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."},{"issue":"4","key":"10.1016\/j.neucom.2026.133665_bib0105","doi-asserted-by":"crossref","first-page":"666","DOI":"10.1109\/JSTSP.2022.3159032","article-title":"CIMFNet: cross-layer interaction and multiscale fusion network for semantic segmentation of high-resolution remote sensing images","volume":"16","author":"Zhou","year":"2022","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"10.1016\/j.neucom.2026.133665_bib0110","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10012","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"issue":"5","key":"10.1016\/j.neucom.2026.133665_bib0115","doi-asserted-by":"crossref","first-page":"1294","DOI":"10.3390\/rs14051294","article-title":"Efficient depth fusion transformer for aerial image semantic segmentation","volume":"14","author":"Yan","year":"2022","journal-title":"Remote Sens."},{"key":"10.1016\/j.neucom.2026.133665_bib0120","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7077","article-title":"Multi-modal fusion transformer for end-to-end autonomous driving","author":"Prakash","year":"2021"},{"key":"10.1016\/j.neucom.2026.133665_bib0125","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.126914","article-title":"Weed mapping in multispectral drone imagery using lightweight vision transformers","volume":"562","author":"Castellano","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133665_bib0130","first-page":"1","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.neucom.2026.133665_bib0135","first-page":"1","article-title":"FTransDeepLab: multimodal fusion transformer-based DeepLabV3+ for remote sensing semantic segmentation","volume":"63","author":"Feng","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.neucom.2026.133665_bib0140","first-page":"1","article-title":"Multispectral fusion transformer network for rgb-thermal urban scene semantic segmentation","volume":"19","author":"Zhou","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"10.1016\/j.neucom.2026.133665_bib0145","first-page":"1","article-title":"RS-mamba for large remote sensing image dense prediction","volume":"62","author":"Zhao","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.neucom.2026.133665_bib0150","first-page":"1","article-title":"ChangeMamba: remote sensing Change detection with spatiotemporal state space model","volume":"62","author":"Chen","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.neucom.2026.133665_bib0155","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"5793","article-title":"RGBT tracking via all-layer multimodal interactions with progressive fusion mamba","volume":"vol. 39","author":"Lu","year":"2025"},{"key":"10.1016\/j.neucom.2026.133665_bib0160","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"1689","article-title":"Wavelet-SRNet: a wavelet-based CNN for multi-scale face super resolution","author":"Huang","year":"2017"},{"issue":"7","key":"10.1016\/j.neucom.2026.133665_bib0165","doi-asserted-by":"crossref","first-page":"1667","DOI":"10.1109\/TMM.2019.2957990","article-title":"IWave: CNN-based wavelet-like transform for image compression","volume":"22","author":"Ma","year":"2019","journal-title":"IEEE Trans. Multimed."},{"issue":"6","key":"10.1016\/j.neucom.2026.133665_bib0170","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3484440","article-title":"Multi-stage fusion and multi-source attention network for multi-modal remote sensing image segmentation","volume":"12","author":"Zhao","year":"2021","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"10.1016\/j.neucom.2026.133665_bib0175","first-page":"1","article-title":"SFFNet: a wavelet-based spatial and frequency domain fusion network for remote sensing segmentation","volume":"62","author":"Yang","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.neucom.2026.133665_bib0180","doi-asserted-by":"crossref","first-page":"7526","DOI":"10.1109\/TCSVT.2025.3549459","article-title":"WaveFusion: a novel wavelet vision transformer with Saliency-Guided enhancement for multimodal image fusion","volume":"35","author":"Wang","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.133665_bib0185","author":"Wang"},{"key":"10.1016\/j.neucom.2026.133665_bib0190","author":"Chen"},{"key":"10.1016\/j.neucom.2026.133665_bib0195","author":"Zhu"},{"key":"10.1016\/j.neucom.2026.133665_bib0200","series-title":"European Conference on Computer Vision","first-page":"363","article-title":"Wavelet convolutions for large receptive fields","author":"Finder","year":"2024"},{"key":"10.1016\/j.neucom.2026.133665_bib0205","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10781","article-title":"EfficientDet: scalable and efficient object detection","author":"Tan","year":"2020"},{"key":"10.1016\/j.neucom.2026.133665_bib0210","author":"Liu"},{"key":"10.1016\/j.neucom.2026.133665_bib0215","unstructured":"Vaihingen, ISPRS, 2D semantic labeling dataset, 2018."},{"key":"10.1016\/j.neucom.2026.133665_bib0220","unstructured":"Potsdam, ISPRS, 2D semantic labeling dataset, Accessed: Apr, 2018."},{"key":"10.1016\/j.neucom.2026.133665_bib0225","series-title":"European Conference on Computer Vision","first-page":"205","article-title":"Swin-UNet: unet-like pure transformer for medical image segmentation","author":"Cao","year":"2022"},{"issue":"16","key":"10.1016\/j.neucom.2026.133665_bib0230","doi-asserted-by":"crossref","first-page":"3065","DOI":"10.3390\/rs13163065","article-title":"Transformer meets convolution: a bilateral awareness network for semantic segmentation of very fine resolution urban scene images","volume":"13","author":"Wang","year":"2021","journal-title":"Remote Sens."},{"key":"10.1016\/j.neucom.2026.133665_bib0235","series-title":"European Conference on Computer Vision","first-page":"561","article-title":"Bi-directional cross-modality feature propagation with separation-and-aggregation gate for RGB-d semantic segmentation","author":"Chen","year":"2020"},{"key":"10.1016\/j.neucom.2026.133665_bib0240","series-title":"2021 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"13525","article-title":"Efficient RGB-d semantic segmentation for indoor scene analysis","author":"Seichter","year":"2021"},{"issue":"12","key":"10.1016\/j.neucom.2026.133665_bib0245","doi-asserted-by":"crossref","first-page":"7737","DOI":"10.1109\/TCSVT.2023.3281419","article-title":"SGFNet: semantic-guided fusion network for RGB-thermal semantic segmentation","volume":"33","author":"Wang","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.133665_bib0250","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.neucom.2026.133665_bib0255","article-title":"CSFAFormer: Category-Selective feature aggregation transformer for multimodal remote sensing image semantic segmentation","author":"Ni","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.neucom.2026.133665_bib0260","first-page":"1","article-title":"MGFNet: a multiscale gated fusion network for multimodal semantic segmentation","author":"Wu","year":"2025","journal-title":"Vis. Comput."}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226010623?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226010623?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T13:55:04Z","timestamp":1778766904000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226010623"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":52,"alternative-id":["S0925231226010623"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133665","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"WAMNet: Wavelet-enhanced asymmetric mamba network for semantic segmentation of multimodal remote sensing images","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133665","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133665"}}