{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T23:32:27Z","timestamp":1784071947853,"version":"3.55.0"},"reference-count":40,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100007620","name":"Department of Education of Liaoning Province","doi-asserted-by":"publisher","award":["LJ22241 0146057"],"award-info":[{"award-number":["LJ22241 0146057"]}],"id":[{"id":"10.13039\/501100007620","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007620","name":"Department of Education of Liaoning Province","doi-asserted-by":"publisher","award":["LJ212410146040"],"award-info":[{"award-number":["LJ212410146040"]}],"id":[{"id":"10.13039\/501100007620","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010097","name":"China Association for Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010097","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376036"],"award-info":[{"award-number":["62376036"]}],"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":["52574151"],"award-info":[{"award-number":["52574151"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113625","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T06:44:25Z","timestamp":1774939465000},"page":"113625","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"PB","title":["FTransMamba: A multi-stage fusion transformer and mamba modeling for multimodal remote sensing scene understanding"],"prefix":"10.1016","volume":"179","author":[{"given":"Zhengpeng","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weichun","family":"Guan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Miao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kunyang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiguo","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiansheng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113625_bib0001","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110959","article-title":"Multimodal self-supervised learning for remote sensing data land cover classification","volume":"157","author":"Xue","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113625_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112968","article-title":"DisasterKD: frequency-guided cross-decoder knowledge distillation for UAV real-time disaster damage assessment","volume":"174","author":"Guo","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113625_bib0003","first-page":"1","article-title":"Enhanced deep image prior for unsupervised hyperspectral image super-resolution","volume":"63","author":"Li","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113625_bib0004","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1016\/j.inffus.2016.12.001","article-title":"Multi-focus image fusion with a deep convolutional neural network","volume":"36","author":"Liu","year":"2017","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.patcog.2026.113625_bib0005","first-page":"1","article-title":"Model-informed multistage unsupervised network for hyperspectral image super-resolution","volume":"62","author":"Li","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113625_bib0006","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.patcog.2026.113625_bib0007","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2024.3433619","article-title":"IG-GAN: Interactive guided generative adversarial networks for multimodal image fusion","author":"Sui","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113625_bib0008","article-title":"FTransDeepLab: multimodal fusion transformer-based DeepLabv3+ for remote sensing semantic segmentation","author":"Feng","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113625_bib0009","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1016\/j.isprsjprs.2023.04.008","article-title":"Aligning semantic distribution in fusing optical and SAR images for land use classification","volume":"199","author":"Li","year":"2023","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113625_bib0010","first-page":"1","article-title":"X-shaped Interactive autoencoders with cross-modality mutual learning for unsupervised hyperspectral image super-resolution","volume":"61","author":"Li","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113625_bib0011","article-title":"Difference-complementary learning and label reassignment for multimodal semi-supervised semantic segmentation of remote sensing images","author":"Han","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113625_bib0012","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."},{"issue":"16","key":"10.1016\/j.patcog.2026.113625_bib0013","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.patcog.2026.113625_bib0014","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1016\/j.isprsjprs.2022.06.008","article-title":"UNetFormer: a UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery","volume":"190","author":"Wang","year":"2022","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113625_bib0015","first-page":"1","article-title":"A novel transformer based semantic segmentation scheme for fine-resolution remote sensing images","volume":"19","author":"Wang","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"10.1016\/j.patcog.2026.113625_bib0016","article-title":"Sam-assisted remote sensing imagery semantic segmentation with object and boundary constraints","author":"Ma","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113625_bib0017","article-title":"Sam enhanced semantic segmentation for remote sensing imagery without additional training","author":"Qiao","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113625_bib0018","doi-asserted-by":"crossref","DOI":"10.1109\/JSTARS.2024.3403854","article-title":"MMLN: multi-directional and multi-constraint learning network for remote sensing imagery semantic segmentation","author":"Sun","year":"2024","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113625_bib0019","doi-asserted-by":"crossref","first-page":"824","DOI":"10.1016\/j.isprsjprs.2025.01.017","article-title":"Accurate semantic segmentation of very high-resolution remote sensing images considering feature state sequences: from benchmark datasets to urban applications","volume":"220","author":"Wang","year":"2025","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113625_bib0020","article-title":"PPMamba: enhancing semantic segmentation in remote sensing imagery by SS2d","author":"Mu","year":"2024","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"10.1016\/j.patcog.2026.113625_bib0021","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.patcog.2026.113625_bib0022","article-title":"An implicit transformer-based fusion method for hyperspectral and multispectral remote sensing image","volume":"131","author":"Zhu","year":"2024","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"10.1016\/j.patcog.2026.113625_bib0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103261","article-title":"A spatial-frequency dual-domain implicit guidance method for hyperspectral and multispectral remote sensing image fusion based on Kolmogorov\u2013Arnold network","author":"Zhu","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.patcog.2026.113625_bib0024","article-title":"EMSNet: efficient multimodal symmetric network for semantic segmentation of urban scene from remote sensing imagery","author":"Zhou","year":"2025","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113625_bib0025","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/j.isprsjprs.2024.06.001","article-title":"CloudSeg: a multi-modal learning framework for robust land cover mapping under cloudy conditions","volume":"214","author":"Xu","year":"2024","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113625_bib0026","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.121999","article-title":"Progressive adjacent-layer coordination symmetric cascade network for semantic segmentation of multimodal remote sensing images","volume":"238","author":"Fan","year":"2024","journal-title":"Expert Syst. Appl."},{"issue":"12","key":"10.1016\/j.patcog.2026.113625_bib0027","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.patcog.2026.113625_bib0028","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.patcog.2026.113625_bib0029","first-page":"1","article-title":"QIS-GAN: a lightweight adversarial network with quadtree implicit sampling for multispectral and hyperspectral image fusion","volume":"61","author":"Zhu","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113625_bib0030","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.patcog.2026.113625_bib0031","first-page":"1","article-title":"Mamba collaborative implicit neural representation for hyperspectral and multispectral remote sensing image fusion","volume":"63","author":"Zhu","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113625_bib0032","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103671","article-title":"Semantic segmentation with scale alignment and contextual information fusion for multimodal remote sensing images","volume":"126","author":"Li","year":"2026","journal-title":"Inf. Fusion"},{"issue":"10","key":"10.1016\/j.patcog.2026.113625_bib0033","doi-asserted-by":"crossref","first-page":"9837","DOI":"10.1109\/TCSVT.2025.3560615","article-title":"Semi-mamba: mamba-driven semi-supervised multimodal remote sensing feature classification","volume":"35","author":"Li","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113625_bib0034","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103334","article-title":"SeaMo: a season-aware multimodal foundation model for remote sensing","volume":"125","author":"Li","year":"2026","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.patcog.2026.113625_bib0035","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1016\/j.isprsjprs.2024.09.025","article-title":"ASANet: Asymmetric semantic aligning network for RGB and SAR image land cover classification","volume":"218","author":"Zhang","year":"2024","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113625_bib0036","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112387","article-title":"BCLNet: boundary contrastive learning with gated attention feature fusion and multi-branch spatial-channel reconstruction for land use classification","volume":"302","author":"Yue","year":"2024","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.patcog.2026.113625_bib0037","article-title":"MCANet: a joint semantic segmentation framework of optical and SAR images for land use classification","volume":"106","author":"Li","year":"2022","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"10.1016\/j.patcog.2026.113625_bib0038","article-title":"A unified framework with multimodal fine-tuning for remote sensing semantic segmentation","author":"Ma","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113625_bib0039","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.patcog.2026.113625_bib0040","doi-asserted-by":"crossref","DOI":"10.1109\/JSTARS.2024.3486906","article-title":"Adjacent-scale multimodal fusion networks for semantic segmentation of remote sensing data","author":"Ma","year":"2024","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S003132032600590X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S003132032600590X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T21:19:41Z","timestamp":1781299181000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S003132032600590X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":40,"alternative-id":["S003132032600590X"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113625","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"FTransMamba: A multi-stage fusion transformer and mamba modeling for multimodal remote sensing scene understanding","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113625","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":"113625"}}