{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T05:10:16Z","timestamp":1778821816793,"version":"3.51.4"},"reference-count":46,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62401196"],"award-info":[{"award-number":["62401196"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Jiangsu Province Natural Science Foundation","doi-asserted-by":"publisher","award":["BK20241508"],"award-info":[{"award-number":["BK20241508"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFC3210801"],"award-info":[{"award-number":["2024YFC3210801"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["B250201044"],"award-info":[{"award-number":["B250201044"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Sciences"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.ins.2026.123489","type":"journal-article","created":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:45:22Z","timestamp":1775666722000},"page":"123489","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Frequency\u2013spatial decoupled co-modeling transformer for fine-grained remote sensing image segmentation"],"prefix":"10.1016","volume":"747","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0576-3181","authenticated-orcid":false,"given":"Xin","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shangtuo","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongze","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiwei","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0702-0325","authenticated-orcid":false,"given":"Zhennan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andr\u00e9","family":"Kaup","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.ins.2026.123489_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2020.114417","article-title":"A review of deep learning methods for semantic segmentation of remote sensing imagery","volume":"169","author":"Yuan","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.ins.2026.123489_bib0010","article-title":"Pixel-associated autoencoder for hyperspectral anomaly detection","volume":"129","author":"Xiang","year":"2024","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"10.1016\/j.ins.2026.123489_bib0015","first-page":"1","article-title":"Frequency-guided denoising network for semantic segmentation of remote sensing images","author":"Li","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.ins.2026.123489_bib0020","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.ins.2026.123489_bib0025","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.isprsjprs.2020.01.013","article-title":"ResUNet-a: a deep learning framework for smantic segmentation of remotely sensed data","volume":"162","author":"Diakogiannis","year":"2020","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.ins.2026.123489_bib0030","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"234","article-title":"U-net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"issue":"4","key":"10.1016\/j.ins.2026.123489_bib0035","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs","volume":"40","author":"Chen","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.ins.2026.123489_bib0040","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"key":"10.1016\/j.ins.2026.123489_bib0045","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.ins.2026.123489_bib0050","series-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3141","article-title":"Dual attention network for scene segmentation","author":"Fu","year":"2019"},{"key":"10.1016\/j.ins.2026.123489_bib0055","doi-asserted-by":"crossref","first-page":"717","DOI":"10.1109\/TIP.2024.3523799","article-title":"Attention guidance by cross-domain supervision signals for scene text recognition","volume":"34","author":"Xue","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.ins.2026.123489_bib0060","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"7262","article-title":"Segmenter: transformer for semantic segmentation","author":"Strudel","year":"2021"},{"key":"10.1016\/j.ins.2026.123489_bib0065","series-title":"Proceedings of 2021 IEEE\/CVF International Conference on Computer Vision","first-page":"9992","article-title":"Swin transformer-hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.ins.2026.123489_bib0070","author":"Dosovitskiy"},{"key":"10.1016\/j.ins.2026.123489_bib0075","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/LGRS.2023.3323657","article-title":"Integrating spatial details with long-range contexts for semantic segmentation of very high-resolution remote-sensing images","volume":"20","author":"Long","year":"2023","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"10.1016\/j.ins.2026.123489_bib0080","first-page":"1","article-title":"Aaformer: attention-attended transformer for semantic segmentation of remote sensing images","volume":"21","author":"Li","year":"2024","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"issue":"11","key":"10.1016\/j.ins.2026.123489_bib0085","doi-asserted-by":"crossref","first-page":"9413","DOI":"10.1007\/s13042-025-02761-3","article-title":"Droformer: temporal action detection with drop mechanism of attention","volume":"16","author":"Lee","year":"2025","journal-title":"Int. J. Mach. Learn. Cybern."},{"issue":"1","key":"10.1016\/j.ins.2026.123489_bib0090","doi-asserted-by":"crossref","first-page":"599","DOI":"10.1007\/s13042-024-02262-9","article-title":"Hogformer: high-order graph convolution transformer for 3d human pose estimation","volume":"16","author":"Xie","year":"2025","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"10.1016\/j.ins.2026.123489_bib0095","article-title":"Structure-aware contrastive learning for glomerulus segmentation in renal pathology","author":"Wang","year":"2025","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.ins.2026.123489_bib0100","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"783","article-title":"Fcanet: frequency channel attention networks","author":"Qin","year":"2021"},{"key":"10.1016\/j.ins.2026.123489_bib0105","doi-asserted-by":"crossref","first-page":"4757","DOI":"10.1109\/TIP.2023.3305090","article-title":"Fsanet: frequency self-attention for semantic segmentation","volume":"32","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Image Process: a publication of the IEEE Signal Processing Society"},{"key":"10.1016\/j.ins.2026.123489_bib0110","doi-asserted-by":"crossref","first-page":"1369","DOI":"10.1109\/LSP.2024.3398358","article-title":"A frequency domain feature-guided network for semantic segmentation of remote sensing images","volume":"31","author":"Li","year":"2024","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.ins.2026.123489_bib0115","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2025.122639","article-title":"Spatial-frequency collaborative feature constraint based on interval type-2 fuzzy set and wavelet transform for high-resolution remote sensing image segmentation","author":"Chong","year":"2025","journal-title":"Inf. Sci."},{"key":"10.1016\/j.ins.2026.123489_bib0120","doi-asserted-by":"crossref","first-page":"5341","DOI":"10.1109\/TIP.2025.3587579","article-title":"Uncertainty-aware transformer for referring camouflaged object detection","volume":"34","author":"Wu","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.ins.2026.123489_bib0125","first-page":"1","article-title":"Multi-granularity aggregation network for remote sensing few-shot segmentation","volume":"63","author":"Peng","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.ins.2026.123489_bib0130","first-page":"1","article-title":"Causal prototype-inspired contrast adaptation for unsupervised domain adaptive semantic segmentation of high-resolution remote sensing imagery","author":"Zhu","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.ins.2026.123489_bib0135","first-page":"1","article-title":"Joint spatial and spectral graph-based consistent self-representation for unsupervised hyperspectral band selection","volume":"62","author":"Ma","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"5","key":"10.1016\/j.ins.2026.123489_bib0140","doi-asserted-by":"crossref","first-page":"905","DOI":"10.1109\/LGRS.2020.2988294","article-title":"SCAttNet: semantic segmentation network with spatial and channel attention mechanism for high-resolution remote sensing images","volume":"18","author":"Li","year":"2021","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"issue":"1","key":"10.1016\/j.ins.2026.123489_bib0145","doi-asserted-by":"crossref","first-page":"426","DOI":"10.1109\/TGRS.2020.2994150","article-title":"LANet: local attention embedding to improve the semantic segmentation of remote sensing images","volume":"59","author":"Ding","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.ins.2026.123489_bib0150","first-page":"1","article-title":"Hybrid multiple attention network for semantic segmentation in aerial images","volume":"60","author":"Niu","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"1","key":"10.1016\/j.ins.2026.123489_bib0155","doi-asserted-by":"crossref","first-page":"2844","DOI":"10.1080\/17538947.2023.2241435","article-title":"Mdsnet: a multiscale decoupled supervision network for semantic segmentation of remote sensing images","volume":"16","author":"Feng","year":"2023","journal-title":"Int. J. Digit. Earth"},{"issue":"1","key":"10.1016\/j.ins.2026.123489_bib0160","doi-asserted-by":"crossref","DOI":"10.1080\/15481603.2024.2356355","article-title":"Boundary-enhanced dual-stream network for semantic segmentation of high-resolution remote sensing images","volume":"61","author":"Li","year":"2024","journal-title":"Giscience Remote Sens."},{"key":"10.1016\/j.ins.2026.123489_bib0165","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.124019","article-title":"Remote sensing image semantic segmentation via class-guided structural interaction and boundary perception","volume":"252","author":"He","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.ins.2026.123489_bib0170","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."},{"key":"10.1016\/j.ins.2026.123489_bib0175","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"14247","article-title":"Mindtuner: cross-subject visual decoding with visual fingerprint and semantic correction","volume":"vol. 39","author":"Gong","year":"2025"},{"key":"10.1016\/j.ins.2026.123489_bib0180","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2023.119364","article-title":"High-order paired-aspp for deep semantic segmentation networks","volume":"646","author":"Sun","year":"2023","journal-title":"Inf. Sci."},{"key":"10.1016\/j.ins.2026.123489_bib0185","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.ins.2026.123489_bib0190","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.127347","article-title":"Adaptive sparse lightweight multi-scale hybrid network for remote sensing image semantic segmentation","volume":"280","author":"Sun","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.ins.2026.123489_bib0195","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.127760","article-title":"Spatial and learnable frequency dynamic collaborative visual perception network for remote sensing images semantic segmentation","author":"Cheng","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.ins.2026.123489_bib0200","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.123616","article-title":"Semantic segmentation of remote sensing images based on multiscale features and global information modeling","volume":"249","author":"Gao","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.ins.2026.123489_bib0205","doi-asserted-by":"crossref","first-page":"11750","DOI":"10.1109\/JSTARS.2021.3125107","article-title":"CFCANet: a complete frequency channel attention network for SAR image scene classification","volume":"14","author":"Su","year":"2021","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"10.1016\/j.ins.2026.123489_bib0210","first-page":"37928","article-title":"Learnability matters: active learning for video captioning","volume":"37","author":"Zhang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ins.2026.123489_bib0215","unstructured":"ISPRS, ISPRS 2d semantic labeling contest - potsdam, https:\/\/www.isprs.org\/education\/benchmarks\/UrbanSemLab\/2d-sem-label-potsdam.aspx"},{"key":"10.1016\/j.ins.2026.123489_bib0220","author":"Wang"},{"key":"10.1016\/j.ins.2026.123489_bib0225","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."},{"issue":"9","key":"10.1016\/j.ins.2026.123489_bib0230","doi-asserted-by":"crossref","first-page":"2293","DOI":"10.3390\/rs15092293","article-title":"Dynamic high-resolution network for semantic segmentation in remote-sensing images","volume":"15","author":"Guo","year":"2023","journal-title":"Remote Sens."}],"container-title":["Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025526004202?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025526004202?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T04:26:02Z","timestamp":1778819162000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0020025526004202"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":46,"alternative-id":["S0020025526004202"],"URL":"https:\/\/doi.org\/10.1016\/j.ins.2026.123489","relation":{},"ISSN":["0020-0255"],"issn-type":[{"value":"0020-0255","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Frequency\u2013spatial decoupled co-modeling transformer for fine-grained remote sensing image segmentation","name":"articletitle","label":"Article Title"},{"value":"Information Sciences","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ins.2026.123489","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":"123489"}}