{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,31]],"date-time":"2026-05-31T21:02:52Z","timestamp":1780261372769,"version":"3.54.0"},"reference-count":62,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"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":["Neurocomputing"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.neucom.2026.134039","type":"journal-article","created":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T06:50:29Z","timestamp":1779346229000},"page":"134039","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Hierarchical fusion of local and global visual features with mixture-of-experts for remote sensing image scene classification"],"prefix":"10.1016","volume":"695","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3225-4892","authenticated-orcid":false,"given":"Yuanhao","family":"Tang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3743-7738","authenticated-orcid":false,"given":"Xuechao","family":"Zou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8497-4782","authenticated-orcid":false,"given":"Zhengpei","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6801-0510","authenticated-orcid":false,"given":"Junliang","family":"Xing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3188-6583","authenticated-orcid":false,"given":"Chengkun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2234-2696","authenticated-orcid":false,"given":"Jianqiang","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134039_bib0005","article-title":"A spectral-spatial-dependent global learning framework for insufficient and imbalanced hyperspectral image classification","author":"Zhu","year":"2021","journal-title":"IEEE Trans. Cybern."},{"issue":"2","key":"10.1016\/j.neucom.2026.134039_bib0010","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1109\/MGRS.2013.2244672","article-title":"Hyperspectral remote sensing data analysis and future challenges","volume":"1","author":"Bioucas-Dias","year":"2013","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"10.1016\/j.neucom.2026.134039_bib0015","article-title":"Beyond the patchwise classification: spectral-spatial fully convolutional networks for hyperspectral image classification","author":"Yonghao","year":"2019","journal-title":"IEEE Trans. Big Data"},{"issue":"11","key":"10.1016\/j.neucom.2026.134039_bib0020","doi-asserted-by":"crossref","first-page":"5345","DOI":"10.1109\/TIP.2016.2601268","article-title":"Beyond the sparsity-based target detector: a hybrid sparsity and statistics-based detector for hyperspectral images","volume":"25","author":"Du","year":"2016","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.neucom.2026.134039_bib0025","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1016\/j.isprsjprs.2021.11.021","article-title":"Hyperloopnet: hyperspectral image classification using multiscale self-looping convolutional networks","volume":"183","author":"Pande","year":"2022","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.neucom.2026.134039_bib0030","series-title":"ACM SIGSPATIAL GIS 2010","first-page":"270","article-title":"Bag-of-visual-words and spatial extensions for land-use classification","author":"Yang","year":"2010"},{"issue":"10","key":"10.1016\/j.neucom.2026.134039_bib0035","doi-asserted-by":"crossref","first-page":"1865","DOI":"10.1109\/JPROC.2017.2675998","article-title":"Remote sensing image scene classification: benchmark and state of the art","volume":"105","author":"Cheng","year":"2017","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.neucom.2026.134039_bib0040","first-page":"1","article-title":"Resolution-agnostic remote sensing scene classification with implicit neural representations","volume":"20","author":"Chen","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"issue":"7","key":"10.1016\/j.neucom.2026.134039_bib0045","doi-asserted-by":"crossref","first-page":"3965","DOI":"10.1109\/TGRS.2017.2685945","article-title":"Aid: a benchmark data set for performance evaluation of aerial scene classification","volume":"55","author":"Xia","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"6","key":"10.1016\/j.neucom.2026.134039_bib0050","article-title":"Deep learning for remote sensing image classification: a survey","volume":"8","author":"Ying","year":"2018","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."},{"issue":"1","key":"10.1016\/j.neucom.2026.134039_bib0055","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1186\/s40537-023-00772-x","article-title":"Review of deep learning methods for remote sensing satellite images classification: experimental survey and comparative analysis","volume":"10","author":"Adegun","year":"2023","journal-title":"J. Big Data"},{"key":"10.1016\/j.neucom.2026.134039_bib0060","doi-asserted-by":"crossref","first-page":"4325","DOI":"10.1109\/JSTARS.2020.3011333","article-title":"A deep neural network combined CNN and GCN for remote sensing scene classification","volume":"13","author":"Liang","year":"2020","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"issue":"11","key":"10.1016\/j.neucom.2026.134039_bib0065","doi-asserted-by":"crossref","first-page":"2270","DOI":"10.11834\/jrs.20210587","article-title":"CNN-GCN-based dual-stream network for scene classification of remote sensing images","volume":"25","author":"Peifang","year":"2021","journal-title":"Natl. Remote Sens. Bull."},{"key":"10.1016\/j.neucom.2026.134039_bib0070","author":"Castelluccio"},{"key":"10.1016\/j.neucom.2026.134039_bib0075","series-title":"2023 International Symposium on Image and Signal Processing and Analysis (ISPA)","first-page":"1","article-title":"A light-weight deep learning model for remote sensing image classification","author":"Pham","year":"2023"},{"issue":"20","key":"10.1016\/j.neucom.2026.134039_bib0080","doi-asserted-by":"crossref","first-page":"4143","DOI":"10.3390\/rs13204143","article-title":"Trs: transformers for remote sensing scene classification","volume":"13","author":"Zhang","year":"2021","journal-title":"Remote Sens."},{"issue":"3","key":"10.1016\/j.neucom.2026.134039_bib0085","doi-asserted-by":"crossref","first-page":"516","DOI":"10.3390\/rs13030516","article-title":"Vision transformers for remote sensing image classification","volume":"13","author":"Bazi","year":"2021","journal-title":"Remote Sens."},{"key":"10.1016\/j.neucom.2026.134039_bib0090","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.2026.134039_bib0095","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11963","article-title":"Scaling up your kernels to 31x31: revisiting large kernel design in CNNS","author":"Ding","year":"2022"},{"key":"10.1016\/j.neucom.2026.134039_bib0100","series-title":"Advances in Neural Information Processing Systems 29","article-title":"Understanding the effective receptive field in deep convolutional neural networks","author":"Luo","year":"2016"},{"key":"10.1016\/j.neucom.2026.134039_bib0105","article-title":"VM-UNet: vision Mamba UNet for medical image segmentation","author":"Ruan","year":"2024","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"10.1016\/j.neucom.2026.134039_bib0110","first-page":"30","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134039_bib0115","series-title":"International Conference on Machine Learning, PMLR","first-page":"62429","article-title":"Vision Mamba: efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024"},{"key":"10.1016\/j.neucom.2026.134039_bib0120","series-title":"Modeling Sequences with Structured State Spaces","author":"Albert","year":"2023"},{"key":"10.1016\/j.neucom.2026.134039_bib0125","first-page":"572","article-title":"Combining recurrent, convolutional, and continuous-time models with linear state space layers","volume":"34","author":"Albert","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134039_bib0130","series-title":"International Conference on Learning Representations","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Albert","year":"2022"},{"key":"10.1016\/j.neucom.2026.134039_bib0135","author":"Albert"},{"key":"10.1016\/j.neucom.2026.134039_bib0140","author":"Jun"},{"key":"10.1016\/j.neucom.2026.134039_bib0145","author":"Rui"},{"key":"10.1016\/j.neucom.2026.134039_bib0150","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6813","article-title":"VMamba: visual state space model","author":"Liu","year":"2024"},{"key":"10.1016\/j.neucom.2026.134039_bib0155","author":"Oshima"},{"key":"10.1016\/j.neucom.2026.134039_bib0160","first-page":"1","article-title":"RSMamba: remote sensing image classification with state space model","volume":"21","author":"Chen","year":"2024","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"10.1016\/j.neucom.2026.134039_bib0165","author":"Liang"},{"key":"10.1016\/j.neucom.2026.134039_bib0170","article-title":"HC-Mamba: remote sensing image classification via hybrid cross-activation state space model","author":"Yang","year":"2025","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"issue":"5","key":"10.1016\/j.neucom.2026.134039_bib0175","doi-asserted-by":"crossref","first-page":"1007","DOI":"10.1080\/01431160512331314083","article-title":"Support vector machines for classification in remote sensing","volume":"26","author":"Pal","year":"2005","journal-title":"Int. J. Remote Sens."},{"issue":"1","key":"10.1016\/j.neucom.2026.134039_bib0180","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1186\/s13640-018-0398-z","article-title":"Remote sensing scene classification based on rotation-invariant feature learning and joint decision making","volume":"2019","author":"Zhou","year":"2019","journal-title":"EURASIP J. Image Video Process."},{"key":"10.1016\/j.neucom.2026.134039_bib0185","series-title":"Proc. CVPR","first-page":"770","article-title":"Deep residual learning for image recognition","author":"Kaiming","year":"2016"},{"issue":"2","key":"10.1016\/j.neucom.2026.134039_bib0190","doi-asserted-by":"crossref","first-page":"1155","DOI":"10.1109\/TGRS.2018.2864987","article-title":"Scene classification with recurrent attention of VHR remote sensing images","volume":"57","author":"Wang","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"10","key":"10.1016\/j.neucom.2026.134039_bib0195","first-page":"5751","article-title":"Deep feature aggregation framework driven by graph convolutional network for scene classification in remote sensing","volume":"33","author":"Kejie","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.neucom.2026.134039_bib0200","series-title":"International Conference on Learning Representations","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.neucom.2026.134039_bib0205","series-title":"Proc. ICCV","first-page":"10012","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.neucom.2026.134039_bib0210","first-page":"1","article-title":"Cmtfnet: CNN and multiscale transformer fusion network for remote-sensing image semantic segmentation","volume":"61","author":"Honglin","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.neucom.2026.134039_bib0215","first-page":"1","article-title":"Vision transformer: an excellent teacher for guiding small networks in remote sensing image scene classification","volume":"60","author":"Kejie","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.neucom.2026.134039_bib0220","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"5710","article-title":"Leformer: a hybrid CNN-transformer architecture for accurate lake extraction from remote sensing imagery","author":"Chen","year":"2024"},{"issue":"29","key":"10.1016\/j.neucom.2026.134039_bib0225","doi-asserted-by":"crossref","first-page":"18251","DOI":"10.1007\/s00521-024-10134-0","article-title":"Eganet: elevation-guided attention network for scene classification in panchromatic remote sensing images","volume":"36","author":"Rajeshreddy Datla","year":"2024","journal-title":"Neural Comput. Appl."},{"key":"10.1016\/j.neucom.2026.134039_bib0230","first-page":"1","article-title":"Mambahsi: spatial\u2013spectral Mamba for hyperspectral image classification","volume":"62","author":"Yapeng","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.neucom.2026.134039_bib0235","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."},{"issue":"1","key":"10.1016\/j.neucom.2026.134039_bib0240","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","article-title":"Adaptive mixtures of local experts","volume":"3","author":"Jacobs","year":"1991","journal-title":"Neural Comput."},{"key":"10.1016\/j.neucom.2026.134039_bib0245","author":"Zoph"},{"key":"10.1016\/j.neucom.2026.134039_bib0250","first-page":"8583","article-title":"Scaling vision with sparse mixture of experts","volume":"34","author":"Riquelme","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134039_bib0255","series-title":"IGARSS 2024-2024 IEEE International Geoscience and Remote Sensing Symposium","first-page":"9676","article-title":"Mv-moe: a visual mixture-of-experts model for optical-sar image matching","author":"Cao","year":"2024"},{"key":"10.1016\/j.neucom.2026.134039_bib0260","article-title":"RS-moe: a vision-language model with mixture of experts for remote sensing image captioning and visual question answering","author":"Lin","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.neucom.2026.134039_bib0265","author":"Liu"},{"key":"10.1016\/j.neucom.2026.134039_bib0270","series-title":"International Conference on Machine Learning, PMLR","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2021"},{"key":"10.1016\/j.neucom.2026.134039_bib0275","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"Jie","year":"2018"},{"key":"10.1016\/j.neucom.2026.134039_bib0280","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"3","article-title":"CBAM: convolutional block attention module","author":"Woo","year":"2018"},{"key":"10.1016\/j.neucom.2026.134039_bib0285","series-title":"WACV","first-page":"3559","article-title":"Attentional feature fusion","author":"Dai","year":"2021"},{"key":"10.1016\/j.neucom.2026.134039_bib0290","first-page":"1","article-title":"A dual-stage residual diffusion model with perceptual decoding for remote sensing image dehazing","volume":"63","author":"Zhou","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.neucom.2026.134039_bib0295","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.110410","article-title":"Physical-priors-guided dehazeformer","volume":"266","author":"Zhou","year":"2023","journal-title":"Knowl.-based Syst.","ISSN":"https:\/\/id.crossref.org\/issn\/0950-7051","issn-type":"print"},{"key":"10.1016\/j.neucom.2026.134039_bib0300","first-page":"1","article-title":"Diffcr: a fast conditional diffusion framework for cloud removal from optical satellite images","volume":"62","author":"Zou","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.neucom.2026.134039_bib0305","series-title":"European Conference on Artificial Intelligence (ECAI)","first-page":"3165","article-title":"Pmaa: a progressive multi-scale attention autoencoder model for high-performance cloud removal from multi-temporal satellite imagery","author":"Zou","year":"2023"},{"key":"10.1016\/j.neucom.2026.134039_bib0310","series-title":"ICCV","first-page":"618","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2017"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226014372?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226014372?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,31]],"date-time":"2026-05-31T20:39:17Z","timestamp":1780259957000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226014372"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":62,"alternative-id":["S0925231226014372"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134039","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Hierarchical fusion of local and global visual features with mixture-of-experts for remote sensing image scene classification","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134039","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":"134039"}}