{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T12:03:44Z","timestamp":1780574624537,"version":"3.54.1"},"reference-count":37,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"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":["Information Sciences"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.ins.2026.123713","type":"journal-article","created":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T15:18:55Z","timestamp":1780327135000},"page":"123713","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["CMFA-Net: Cross-modality fused attention network for multimodal aerial scene classification"],"prefix":"10.1016","volume":"754","author":[{"given":"Muhammad Zaheer","family":"Sajid","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad Fareed","family":"Hamid","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"7","key":"10.1016\/j.ins.2026.123713_bib0005","first-page":"4053","article-title":"Remote sensing image scene classification: benchmark and state of the art","volume":"55","author":"Cheng","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"12","key":"10.1016\/j.ins.2026.123713_bib0010","doi-asserted-by":"crossref","first-page":"6899","DOI":"10.1109\/TGRS.2018.2845668","article-title":"Remote sensing scene classification using multilayer stacked covariance pooling","volume":"56","author":"He","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.ins.2026.123713_bib0015","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"10012","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.ins.2026.123713_bib0020","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2022.3225267","article-title":"Spectral\u2013spatial transformer network for hyperspectral image classification: a factorized architecture search framework","volume":"60","author":"Zhong","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.ins.2026.123713_bib0025","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2022.3172371","article-title":"SpectralFormer: rethinking hyperspectral image classification with transformers","volume":"60","author":"Hong","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.ins.2026.123713_bib0030","article-title":"FactoFormer: factorized hyperspectral transformers with self-supervised pretraining","author":"Mohamed","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.ins.2026.123713_bib0035","article-title":"Multiscale spectral\u2013spatial convolutional transformer for hyperspectral image classification","author":"Gong","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.ins.2026.123713_bib0040","article-title":"DiffFormer: differential spatial\u2013spectral transformer for hyperspectral image classification","author":"Ahmad","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.ins.2026.123713_bib0045","article-title":"EnergyFormer: energy attention with Fourier embedding for hyperspectral image classification","author":"Sohail","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.ins.2026.123713_bib0050","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-025-34176-z","article-title":"High-performance scene classification in remote sensing using deep learning","volume":"16","author":"Abdelmonem","year":"2026","journal-title":"Sci. Rep."},{"issue":"3","key":"10.1016\/j.ins.2026.123713_bib0055","doi-asserted-by":"crossref","first-page":"635","DOI":"10.3844\/jcssp.2025.635.645","article-title":"Remote sensing image classification using convolutional neural network (CNN) and transfer learning techniques","volume":"21","author":"Abd Zaid","year":"2025","journal-title":"J. Comput. Sci."},{"key":"10.1016\/j.ins.2026.123713_bib0060","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1016\/j.patcog.2016.07.001","article-title":"Towards better exploiting convolutional neural networks for remote sensing scene classification","volume":"61","author":"Nogueira","year":"2017","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.ins.2026.123713_bib0065","article-title":"Few-shot remote sensing scene classification based on deep feature fusion","author":"Yang","year":"2023","journal-title":"Math. Biosci. Eng."},{"key":"10.1016\/j.ins.2026.123713_bib0070","doi-asserted-by":"crossref","DOI":"10.3389\/fcomp.2025.1613648","article-title":"Improving remote sensing scene classification with data augmentation techniques to mitigate class imbalance","volume":"7","author":"Wang","year":"2025","journal-title":"Front. Comput. Sci."},{"key":"10.1016\/j.ins.2026.123713_bib0075","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.ins.2026.123713_bib0080","doi-asserted-by":"crossref","DOI":"10.3390\/rs16224127","article-title":"Hierarchical spectral\u2013spatial transformer for hyperspectral image classification","volume":"16","author":"Zhu","year":"2024","journal-title":"Remote Sens."},{"issue":"2","key":"10.1016\/j.ins.2026.123713_bib0085","article-title":"TGF-net: transformer and gist CNN fusion network for multi-modal remote sensing image classification","volume":"20","author":"Wang","year":"2025","journal-title":"PLOS ONE"},{"key":"10.1016\/j.ins.2026.123713_bib0090","doi-asserted-by":"crossref","DOI":"10.1016\/j.cosrev.2024.100658","article-title":"Deep learning for hyperspectral image classification: a survey","volume":"53","author":"Kumar","year":"2024","journal-title":"Comput. Sci. Rev."},{"key":"10.1016\/j.ins.2026.123713_bib0095","article-title":"Multiscale spectral\u2013spatial convolutional transformer for hyperspectral image classification","author":"Gong","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.ins.2026.123713_bib0100","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2023.3242346","article-title":"Spectral\u2013spatial morphological attention transformer","author":"Roy","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.ins.2026.123713_bib0105","article-title":"PCET: patch confidence-enhanced transformer with efficient spectral\u2013spatial features for hyperspectral image classification","volume":"136","author":"Fang","year":"2025","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"10.1016\/j.ins.2026.123713_bib0110","author":"Yang"},{"key":"10.1016\/j.ins.2026.123713_bib0115","article-title":"Multimodal fusion transformer for land cover classification","author":"Wang","year":"2025","journal-title":"ISPRS Arch."},{"key":"10.1016\/j.ins.2026.123713_bib0120","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1016\/j.isprsjprs.2024.09.012","article-title":"SoftFormer: SAR-optical fusion transformer for urban land use and land cover classification","volume":"218","author":"Liu","year":"2024","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.ins.2026.123713_bib0125","article-title":"A multiscale transformer with spatial attention for hyperspectral image classification","volume":"16","author":"Ahmad","year":"2026","journal-title":"Sci. Rep."},{"issue":"8","key":"10.1016\/j.ins.2026.123713_bib0130","doi-asserted-by":"crossref","first-page":"1668","DOI":"10.1109\/JAS.2023.123681","article-title":"Hyperspectral image super-resolution meets deep learning: a survey and perspective","volume":"10","author":"Wang","year":"2023","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"10.1016\/j.ins.2026.123713_bib0135","series-title":"Leveraging spatio-temporal patterns for predicting citywide traffic crowd flows using deep hybrid neural networks","first-page":"125","author":"Ali","year":"2019"},{"key":"10.1016\/j.ins.2026.123713_bib0140","doi-asserted-by":"crossref","first-page":"852","DOI":"10.1016\/j.ins.2021.08.042","article-title":"Exploiting dynamic spatio-temporal correlations for citywide traffic flow prediction using attention based neural networks","volume":"577","author":"Ali","year":"2021","journal-title":"Inf. Sci."},{"key":"10.1016\/j.ins.2026.123713_bib0145","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1016\/j.neunet.2021.10.021","article-title":"Exploiting dynamic spatio-temporal graph convolutional neural networks for citywide traffic flows prediction","volume":"145","author":"Ali","year":"2022","journal-title":"Neural Netw."},{"issue":"20","key":"10.1016\/j.ins.2026.123713_bib0150","doi-asserted-by":"crossref","first-page":"31401","DOI":"10.1007\/s11042-020-10486-4","article-title":"A data aggregation based approach to exploit dynamic spatio-temporal correlations for citywide crowd flows prediction in fog computing","volume":"80","author":"Ali","year":"2021","journal-title":"Multimed. Tools Appl."},{"key":"10.1016\/j.ins.2026.123713_bib0155","doi-asserted-by":"crossref","DOI":"10.1016\/j.chaos.2025.116898","article-title":"Dynamic multi-graph spatio-temporal learning for citywide traffic flow prediction in transportation systems","volume":"199","author":"Ali","year":"2025","journal-title":"Chaos Solit. Fractals"},{"key":"10.1016\/j.ins.2026.123713_bib0160","doi-asserted-by":"crossref","DOI":"10.1016\/j.cosrev.2025.100886","article-title":"Advanced computational models for urban traffic flow prediction: a comprehensive review and future directions","volume":"60","author":"Ali","year":"2026","journal-title":"Comput. Sci. Rev."},{"key":"10.1016\/j.ins.2026.123713_bib0165","article-title":"Complementary information-guided interactive fusion network for HSI and LiDAR data joint classification","author":"Xu","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.ins.2026.123713_bib0170","article-title":"Multi-level fusion network based on mix hybrid attention for hyperspectral and LiDAR image classification","author":"He","year":"2025","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"10.1016\/j.ins.2026.123713_bib0175","article-title":"Cross-source transformer-based neighborhood contrastive learning for joint classification of hyperspectral and LiDAR data","author":"Liu","year":"2025","journal-title":"Inf. Fusion"},{"issue":"1","key":"10.1016\/j.ins.2026.123713_bib0180","doi-asserted-by":"crossref","first-page":"138","DOI":"10.3390\/rs18010138","article-title":"Global\u2013local Mamba-based dual-modality fusion for hyperspectral and LiDAR data classification","volume":"18","author":"Hussain","year":"2026","journal-title":"Remote Sens."},{"key":"10.1016\/j.ins.2026.123713_bib0185","author":"Atrisukul"}],"container-title":["Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025526006444?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025526006444?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T11:30:25Z","timestamp":1780572625000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0020025526006444"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":37,"alternative-id":["S0020025526006444"],"URL":"https:\/\/doi.org\/10.1016\/j.ins.2026.123713","relation":{},"ISSN":["0020-0255"],"issn-type":[{"value":"0020-0255","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"CMFA-Net: Cross-modality fused attention network for multimodal aerial scene classification","name":"articletitle","label":"Article Title"},{"value":"Information Sciences","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ins.2026.123713","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"123713"}}