{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T00:09:23Z","timestamp":1779581363477,"version":"3.53.1"},"reference-count":99,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"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":["42271386"],"award-info":[{"award-number":["42271386"]}],"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":["42001313"],"award-info":[{"award-number":["42001313"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2019FY202503"],"award-info":[{"award-number":["2019FY202503"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Applied Soft Computing"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.asoc.2026.115036","type":"journal-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T01:03:13Z","timestamp":1773968593000},"page":"115036","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["HaloSeg: Halo transformer embedding U-Net for local-global feature induced semantic segmentation of high-resolution remote sensing images"],"prefix":"10.1016","volume":"196","author":[{"given":"Han","family":"Zhai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.asoc.2026.115036_bib1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.isprsjprs.2024.03.012","article-title":"Methods and datasets on semantic segmentation for Unmanned Aerial Vehicle remote sensing images: a review","volume":"211","author":"Cheng","year":"2024","journal-title":"ISPRS J. Photo Remote Sens"},{"key":"10.1016\/j.asoc.2026.115036_bib2","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. Photo Remote Sens"},{"key":"10.1016\/j.asoc.2026.115036_bib3","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2025.3609665","article-title":"Local-global spectral-spatial dual deep subspace clustering network for hyperspectral images","volume":"63","author":"Zhai","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens"},{"key":"10.1016\/j.asoc.2026.115036_bib4","article-title":"DWin-HRFormer: a high-resolution transformer model with directional windows for semantic segmentation of urban construction land","volume":"61","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens"},{"issue":"20","key":"10.1016\/j.asoc.2026.115036_bib5","doi-asserted-by":"crossref","first-page":"4139","DOI":"10.3390\/electronics13204139","article-title":"A review of semantic segmentation and instance segmentation techniques in forestry using LiDAR and imagery data","volume":"13","author":"Wo\u0142k","year":"2024","journal-title":"Electronics"},{"key":"10.1016\/j.asoc.2026.115036_bib6","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2019.106971","article-title":"Stacked Fisher autoencoder for SAR change detection","volume":"96","author":"Liu","year":"2019","journal-title":"Pattern Recog"},{"issue":"5","key":"10.1016\/j.asoc.2026.115036_bib7","doi-asserted-by":"crossref","first-page":"901","DOI":"10.3390\/rs13050901","article-title":"Crop row segmentation and detection in paddy fields based on treble-classification otsu and double-dimensional clustering method","volume":"13","author":"Yu","year":"2021","journal-title":"Remote Sens"},{"key":"10.1016\/j.asoc.2026.115036_bib8","doi-asserted-by":"crossref","first-page":"3123","DOI":"10.1109\/JSTARS.2024.3349625","article-title":"TCNet: multiscale fusion of transformer and CNN for semantic segmentation of remote sensing images","volume":"17","author":"Xiang","year":"2024","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens"},{"issue":"2","key":"10.1016\/j.asoc.2026.115036_bib9","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1007\/s11760-024-03766-1","article-title":"Multi-scale attention and boundary-aware network for military camouflaged object detection using unmanned aerial vehicles","volume":"19","author":"Liu","year":"2025","journal-title":"Signal Image Video Process"},{"key":"10.1016\/j.asoc.2026.115036_bib10","doi-asserted-by":"crossref","first-page":"626","DOI":"10.1016\/j.neucom.2022.01.005","article-title":"Review the state-of-the-art technologies of semantic segmentation based on deep learning","volume":"493","author":"Mo","year":"2022","journal-title":"Neurocomput"},{"key":"10.1016\/j.asoc.2026.115036_bib11","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.dsp.2017.02.003","article-title":"Automated segmentation of iris images acquired in an unconstrained environment using HOG-SVM and GrowCut","volume":"64","author":"Radman","year":"2017","journal-title":"Digit. Signal Process"},{"key":"10.1016\/j.asoc.2026.115036_bib12","doi-asserted-by":"crossref","DOI":"10.1016\/j.bdr.2021.100295","article-title":"Regularized least squares twin SVM for multiclass classification","volume":"27","author":"Ali","year":"2022","journal-title":"Big Data Res."},{"key":"10.1016\/j.asoc.2026.115036_bib13","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2021.103207","article-title":"Bias correction of intensity inhomogeneous images hybridized with superpixel segmentation","volume":"71","author":"Li","year":"2022","journal-title":"Biomed. Signal Process. Control"},{"key":"10.1016\/j.asoc.2026.115036_bib14","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1016\/j.isprsjprs.2019.11.006","article-title":"Superpixel-enhanced deep neural forest for remote sensing image semantic segmentation","volume":"159","author":"Mi","year":"2020","journal-title":"ISPRS J. Photo Remote Sens"},{"key":"10.1016\/j.asoc.2026.115036_bib15","doi-asserted-by":"crossref","DOI":"10.1109\/LGRS.2024.3477609","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":"1","key":"10.1016\/j.asoc.2026.115036_bib16","doi-asserted-by":"crossref","DOI":"10.1080\/17538947.2025.2491108","article-title":"Integrating unsupervised domain adaptation and SAM technologies for image semantic segmentation: a case study on building extraction from high-resolution remote sensing images","volume":"18","author":"Yang","year":"2025","journal-title":"Int. J. Digit. Earth"},{"key":"10.1016\/j.asoc.2026.115036_bib17","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2025.3643295","article-title":"Multilevel joint regularizations meet dual self-representations: An innovative deep subspace clustering framework for hyperspectral images","volume":"64","author":"Zhai","year":"2026","journal-title":"IEEE Trans. Geosci. Remote Sens"},{"key":"10.1016\/j.asoc.2026.115036_bib18","article-title":"Enhanced contextual representation with deep neural networks for land cover classification based on remote sensing images","volume":"107","author":"Cheng","year":"2022","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"10.1016\/j.asoc.2026.115036_bib19","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.isprsjprs.2018.01.021","article-title":"Land cover mapping at very high resolution with rotation equivariant CNNs: Towards small yet accurate models","volume":"145","author":"Marcos","year":"2018","journal-title":"ISPRS J. Photo Remote Sens"},{"key":"10.1016\/j.asoc.2026.115036_bib20","first-page":"3431","article-title":"Fully convolutional networks for semantic segmentation, in Proc","author":"Long","year":"2015","journal-title":"IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) Boston USA"},{"key":"10.1016\/j.asoc.2026.115036_bib21","article-title":"Multistage attention ResU-Net for semantic segmentation of fine-resolution remote sensing images","volume":"19","author":"Li","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"issue":"12","key":"10.1016\/j.asoc.2026.115036_bib22","doi-asserted-by":"crossref","first-page":"2172","DOI":"10.1109\/LGRS.2020.3012705","article-title":"MFALNet: A multiscale feature aggregation lightweight network for semantic segmentation of high-resolution remote sensing images","volume":"18","author":"Lv","year":"2021","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"10.1016\/j.asoc.2026.115036_bib23","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015","journal-title":"Proc. Int. Conf. Med. Image Comput. Comput. Assist. Interv. (MICCAI) Munich Ger."},{"key":"10.1016\/j.asoc.2026.115036_bib24","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.isprsjprs.2020.01.013","article-title":"ResUNet-A: A deep learning framework for semantic segmentation of remotely sensed data","volume":"162","author":"Diakogiannis","year":"2020","journal-title":"ISPRS J. Photo Remote Sens"},{"key":"10.1016\/j.asoc.2026.115036_bib25","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1016\/j.isprsjprs.2021.05.004","article-title":"An attention-fused network for semantic segmentation of very-high-resolution remote sensing imagery","volume":"177","author":"Yang","year":"2021","journal-title":"ISPRS J. Photo Remote Sens"},{"key":"10.1016\/j.asoc.2026.115036_bib26","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113233","article-title":"DCSSGA-UNet: Biomedical image segmentation with DenseNet channel spatial and Semantic Guidance Attention","volume":"314","author":"Hussain","year":"2025","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.asoc.2026.115036_bib27","article-title":"arXiv preprint","author":"Chen","year":"2017","journal-title":"Rethink. atrous convolution Semant. Image Segm."},{"key":"10.1016\/j.asoc.2026.115036_bib28","unstructured":"M. Liu, J. Dan, Z. Lu, Y. Yu, Y. Li, X. Li, CM-UNet: Hybrid CNN-Mamba UNet for remote sensing image semantic segmentation, arXiv preprint arXiv:2405.10530, (2024)."},{"issue":"1","key":"10.1016\/j.asoc.2026.115036_bib29","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.asoc.2026.115036_bib30","series-title":"Proc","first-page":"12408","article-title":"A relation-augmented fully convolutional network for semantic segmentation in aerial scenes","author":"Mou","year":"2019"},{"key":"10.1016\/j.asoc.2026.115036_bib31","first-page":"6230","article-title":"Pyramid scene parsing network","author":"Zhao","year":"2017","journal-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) Honol. USA"},{"key":"10.1016\/j.asoc.2026.115036_bib32","first-page":"432","article-title":"Unified perceptual parsing for scene understanding","author":"Xiao","year":"2018","journal-title":"Proc. Eur. Conf. Comput. Vis. (ECCV) Munich Ger."},{"issue":"6","key":"10.1016\/j.asoc.2026.115036_bib33","doi-asserted-by":"crossref","first-page":"2623","DOI":"10.1109\/TIP.2018.2809606","article-title":"Diverse region-based CNN for hyperspectral image classification","volume":"27","author":"Zhang","year":"2018","journal-title":"IEEE Trans. Image Process"},{"key":"10.1016\/j.asoc.2026.115036_bib34","article-title":"Deep multimodal fusion network for semantic segmentation using remote sensing image and LiDAR data","volume":"60","author":"Sun","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens"},{"key":"10.1016\/j.asoc.2026.115036_bib35","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2021.3065112","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"},{"key":"10.1016\/j.asoc.2026.115036_bib36","first-page":"38","article-title":"Transformers: State-of-the-art natural language processing","author":"Wolf","year":"2020","journal-title":"Proc. Conf. Empir. Methods Nat. Lang. Process. (EMNLP) Punta Cana Dominic. Repub."},{"key":"10.1016\/j.asoc.2026.115036_bib37","doi-asserted-by":"crossref","unstructured":"N. Carion, F. Massa, G. Synnaeve, N. Usunier, A. Kirillov, S. Zagoruyko, End-to-end object detection with transformers, in Proc. Eur. Conf. Comput. Vis. (ECCV), vol. 12346, Glasgow, U.K., Aug. 2020, pp. 213\u2013229.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"10.1016\/j.asoc.2026.115036_bib38","first-page":"12294","article-title":"Pre-trained image processing transformer","author":"Chen","year":"2021","journal-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) Kuala Lumpur"},{"key":"10.1016\/j.asoc.2026.115036_bib39","first-page":"538","article-title":"Tokens-to-Token ViT: Training vision transformers from scratch on ImageNet","author":"Yuan","year":"2021","journal-title":"Proc. Int. Conf. Comput. Vis. (ICCV) Montr. Can."},{"issue":"3","key":"10.1016\/j.asoc.2026.115036_bib40","doi-asserted-by":"crossref","first-page":"498","DOI":"10.3390\/rs13030498","article-title":"Spatial\u2013spectral transformer for hyperspectral image classification","volume":"13","author":"He","year":"2021","journal-title":"Remote Sens"},{"key":"10.1016\/j.asoc.2026.115036_bib41","series-title":"Proc","first-page":"6877","article-title":"Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers","author":"Zheng","year":"2021"},{"key":"10.1016\/j.asoc.2026.115036_bib42","first-page":"548","article-title":"Pyramid vision transformer: A versatile backbone for dense prediction without convolutions","author":"Wang","year":"2021","journal-title":"Proc. Int. Conf. Comput. Vis. (ICCV) Montr. Can."},{"key":"10.1016\/j.asoc.2026.115036_bib43","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie","year":"2021"},{"key":"10.1016\/j.asoc.2026.115036_bib44","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.asoc.2026.115036_bib45","first-page":"205","article-title":"Swin-unet: Unet-like pure transformer for medical image segmentation","author":"Cao","year":"2022","journal-title":"Proc. Eur. Conf. Comput. Vis. (ECCV) Tel Aviv Isr. Oct."},{"issue":"1","key":"10.1016\/j.asoc.2026.115036_bib46","first-page":"80","article-title":"Semantic segmentation of remote sensing images based on filtered hybrid attention mechanisms","volume":"33","author":"Ge","year":"2025","journal-title":"Eng. Lett."},{"key":"10.1016\/j.asoc.2026.115036_bib47","doi-asserted-by":"crossref","first-page":"10990","DOI":"10.1109\/JSTARS.2021.3119654","article-title":"STransFuse: Fusing Swin transformer and convolutional neural network for remote sensing image semantic segmentation","volume":"14","author":"Gao","year":"2021","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens"},{"key":"10.1016\/j.asoc.2026.115036_bib48","author":"Chen","year":"2021","journal-title":"TransUNet Transform. Make Strong encoders Med. Image Segm."},{"key":"10.1016\/j.asoc.2026.115036_bib49","first-page":"14","article-title":"TransFuse: Fusing transformers and CNNs for medical image segmentation","author":"Zhang","year":"2021","journal-title":"Proc. Int. Conf. Med. Image Comput. Comput. Assist. Interv. (MICCAI) Strasbg. Fr."},{"key":"10.1016\/j.asoc.2026.115036_bib50","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2022.3144165","article-title":"Swin transformer embedding UNet for remote sensing image semantic segmentation","volume":"60","author":"He","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens"},{"key":"10.1016\/j.asoc.2026.115036_bib51","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2023.3329152","article-title":"Combining Swin transformer with UNet for remote sensing image semantic segmentation","volume":"61","author":"Fan","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens"},{"key":"10.1016\/j.asoc.2026.115036_bib52","article-title":"Enhancing multiscale representations with transformer for remote sensing image semantic segmentation","volume":"61","author":"Xiao","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens"},{"issue":"1","key":"10.1016\/j.asoc.2026.115036_bib53","doi-asserted-by":"crossref","first-page":"6110","DOI":"10.1038\/s41598-025-90518-x","article-title":"Semantic segmentation feature fusion network based on transformer","volume":"15","author":"Li","year":"2025","journal-title":"Sci. Rep."},{"key":"10.1016\/j.asoc.2026.115036_bib54","doi-asserted-by":"crossref","first-page":"608","DOI":"10.1109\/OJSP.2025.3573202","article-title":"Swin Transformer with Spatial and Local Context Augmentation for Enhanced Semantic Segmentation of Remote Sensing Images","volume":"6","author":"Ding","year":"2025","journal-title":"IEEE Open J. Signal Process"},{"key":"10.1016\/j.asoc.2026.115036_bib55","doi-asserted-by":"crossref","DOI":"10.1109\/LGRS.2025.3612187","article-title":"CT-PromptSAM: Collaborative prompting with hybrid CNN\u2013transformer for remote sensing semantic segmentation","volume":"22","author":"Wang","year":"2025","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"10.1016\/j.asoc.2026.115036_bib56","article-title":"CAMformer: A single-stage CNN\u2013transformer hybrid for weakly supervised semantic segmentation in aerial imagery","volume":"64","author":"Zhou","year":"2026","journal-title":"IEEE Trans. Geosci. Remote Sens"},{"key":"10.1016\/j.asoc.2026.115036_bib57","doi-asserted-by":"crossref","DOI":"10.1016\/j.dsp.2025.105852","article-title":"Hybrid transfer semantic segmentation architecture for hyperspectral image classification","author":"Yan","year":"2026","journal-title":"Digit. Signal Process"},{"issue":"9","key":"10.1016\/j.asoc.2026.115036_bib58","doi-asserted-by":"crossref","first-page":"3575","DOI":"10.1080\/01431161.2019.1706009","article-title":"Research on a novel extraction method using Deep Learning based on GF-2 images for aquaculture areas","volume":"41","author":"Cheng","year":"2020","journal-title":"Int. J. Remote Sens"},{"key":"10.1016\/j.asoc.2026.115036_bib59","doi-asserted-by":"crossref","DOI":"10.1109\/LGRS.2023.3261402","article-title":"A self-learning-update CNN model for semantic segmentation of remote sensing images","volume":"20","author":"Zheng","year":"2023","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"10.1016\/j.asoc.2026.115036_bib60","doi-asserted-by":"crossref","first-page":"19378","DOI":"10.1109\/JSTARS.2025.3583558","article-title":"FSDENet: A Frequency and Spatial Domains Based Detail Enhancement Network for Remote Sensing Semantic Segmentation","volume":"18","author":"Fu","year":"2025","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens"},{"key":"10.1016\/j.asoc.2026.115036_bib61","author":"Sun","year":"2019","journal-title":"High. Resolut. Represent. labeling pixels Reg. arXiv Prepr."},{"key":"10.1016\/j.asoc.2026.115036_bib62","series-title":"IEEE Conf. Comput","first-page":"5168","article-title":"RefineNet: Multi-path refinement networks for high-resolution semantic segmentation, in Proc","author":"Lin","year":"2017"},{"key":"10.1016\/j.asoc.2026.115036_bib63","first-page":"1","article-title":"PLFCN: Pyramid loss reinforced fully convolutional network","author":"Liu","year":"2019","journal-title":"Proc. Int. Conf. Distrib. Smart Cameras Sep. (ICDSC) Trento USA"},{"key":"10.1016\/j.asoc.2026.115036_bib64","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1109\/JSTARS.2020.3040176","article-title":"SANet: A sea-land segmentation network via adaptive multiscale feature learning","volume":"14","author":"Cui","year":"2021","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens"},{"key":"10.1016\/j.asoc.2026.115036_bib65","series-title":"Proc","first-page":"3856","article-title":"Semantic segmentation of high-resolution remote sensing image based on batch-attention mechanism","author":"Su","year":"2019"},{"key":"10.1016\/j.asoc.2026.115036_bib66","article-title":"Multistage attention ResU-Net for semantic segmentation of fine-resolution remote sensing images","volume":"19","author":"Li","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"10.1016\/j.asoc.2026.115036_bib67","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2023.3272614","article-title":"Lightweight attention network for very high-resolution image semantic segmentation","volume":"61","author":"Guan","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens"},{"key":"10.1016\/j.asoc.2026.115036_bib68","article-title":"Semantic segmentation of remote-sensing images based on multiscale feature fusion and attention refinement","volume":"19","author":"He","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"issue":"5","key":"10.1016\/j.asoc.2026.115036_bib69","doi-asserted-by":"crossref","first-page":"872","DOI":"10.3390\/rs12050872","article-title":"Multi-scale adaptive feature fusion network for semantic segmentation in remote sensing images","volume":"12","author":"Shang","year":"2020","journal-title":"Remote Sens"},{"key":"10.1016\/j.asoc.2026.115036_bib70","doi-asserted-by":"crossref","first-page":"65347","DOI":"10.1109\/ACCESS.2019.2917952","article-title":"DenseU-net-based semantic segmentation of small objects in urban remote sensing images","volume":"7","author":"Dong","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.asoc.2026.115036_bib71","article-title":"FactSeg: Foreground activation-driven small object semantic segmentation in large-scale remote sensing imagery","volume":"60","author":"Ma","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens"},{"issue":"4","key":"10.1016\/j.asoc.2026.115036_bib72","doi-asserted-by":"crossref","first-page":"3532","DOI":"10.1109\/TGRS.2020.3009143","article-title":"Adaptive effective receptive field convolution for semantic segmentation of VHR remote sensing images","volume":"59","author":"Chen","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens"},{"key":"10.1016\/j.asoc.2026.115036_bib73","series-title":"Proc","first-page":"10323","article-title":"Biformer: Vision transformer with bi-level routing attention","author":"Zhu","year":"2023"},{"key":"10.1016\/j.asoc.2026.115036_bib74","author":"Dosovitskiy","year":"2020","journal-title":"Image Is. worth 16x16 words Transform. Image Recognit. Scale"},{"key":"10.1016\/j.asoc.2026.115036_bib75","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume":"139","author":"Touvron","year":"2021","journal-title":"Proc. Int. Conf. Mach. Learn. Vienna Austria"},{"issue":"1","key":"10.1016\/j.asoc.2026.115036_bib76","doi-asserted-by":"crossref","DOI":"10.1038\/sdata.2018.161","article-title":"The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions","volume":"5","author":"Tschandl","year":"2018","journal-title":"Sci. Data"},{"issue":"12","key":"10.1016\/j.asoc.2026.115036_bib77","doi-asserted-by":"crossref","first-page":"1247","DOI":"10.1038\/s41592-019-0612-7","article-title":"Nucleus segmentation across imaging experiments: The 2018 data science bowl","volume":"16","author":"Caicedo","year":"2019","journal-title":"Nat. Methods"},{"key":"10.1016\/j.asoc.2026.115036_bib78","doi-asserted-by":"crossref","first-page":"5658","DOI":"10.1007\/s10489-024-05457-3","article-title":"Global and edge enhanced transformer for semantic segmentation of remote sensing","volume":"54","author":"Wang","year":"2024","journal-title":"Appl. Intell."},{"key":"10.1016\/j.asoc.2026.115036_bib79","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. Photo Remote Sens"},{"key":"10.1016\/j.asoc.2026.115036_bib80","doi-asserted-by":"crossref","first-page":"12290","DOI":"10.1109\/JSTARS.2025.3565753","article-title":"DE-Unet: Dual-Encoder U-Net for Ultra-High Resolution Remote Sensing Image Segmentation","volume":"18","author":"Liu","year":"2025","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens"},{"key":"10.1016\/j.asoc.2026.115036_bib81","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2024.3393489","article-title":"Multiscale global context network for semantic segmentation of high-resolution remote sensing images","volume":"62","author":"Zeng","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens"},{"key":"10.1016\/j.asoc.2026.115036_bib82","article-title":"UM2Former: U-shaped multimixed transformer network for large-scale hyperspectral image semantic segmentation","volume":"63","author":"Xu","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens"},{"key":"10.1016\/j.asoc.2026.115036_bib83","article-title":"AMMUNet: Multi-Scale Attention Map Merging for Remote Sensing Image Segmentation","volume":"22","author":"Yang","year":"2025","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"10.1016\/j.asoc.2026.115036_bib84","doi-asserted-by":"crossref","first-page":"1329","DOI":"10.1109\/TIP.2023.3242775","article-title":"LSNet: Lightweight spatial boosting network for detecting salient objects in RGB-Thermal images","volume":"32","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Image Process"},{"key":"10.1016\/j.asoc.2026.115036_bib85","doi-asserted-by":"crossref","first-page":"3027","DOI":"10.1109\/TIP.2023.3275538","article-title":"WaveNet: Wavelet network with knowledge distillation for RGB-T salient object detection","volume":"32","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Image Process"},{"issue":"1","key":"10.1016\/j.asoc.2026.115036_bib86","doi-asserted-by":"crossref","first-page":"657","DOI":"10.1109\/TITS.2023.3306368","article-title":"EGFNet: Edge-aware guidance fusion network for RGB\u2013thermal urban scene parsing","volume":"25","author":"Dong","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.asoc.2026.115036_bib87","doi-asserted-by":"crossref","first-page":"2526","DOI":"10.1109\/TMM.2021.3086618","article-title":"MFFENet: Multiscale feature fusion and enhancement network for RGB\u2013thermal urban road scene parsing","volume":"24","author":"Zhou","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.asoc.2026.115036_bib88","doi-asserted-by":"crossref","first-page":"3483","DOI":"10.1109\/TMM.2022.3161852","article-title":"PGDENet: Progressive guided fusion and depth enhancement network for RGB-D indoor scene parsing","volume":"25","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Multimed."},{"issue":"1","key":"10.1016\/j.asoc.2026.115036_bib89","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1109\/TIV.2022.3164899","article-title":"MTANet: Multitask-aware network with hierarchical multimodal fusion for RGB-T urban scene understanding","volume":"8","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"issue":"3","key":"10.1016\/j.asoc.2026.115036_bib90","doi-asserted-by":"crossref","first-page":"1224","DOI":"10.1109\/TCSVT.2021.3077058","article-title":"ECFFNet: Effective and consistent feature fusion network for RGB-T salient object detection","volume":"32","author":"Zhou","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.asoc.2026.115036_bib91","doi-asserted-by":"crossref","first-page":"2192","DOI":"10.1109\/TMM.2021.3077767","article-title":"CCAFNet: Crossflow and cross-scale adaptive fusion network for detecting salient objects in RGB-D images","volume":"24","author":"Zhou","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.asoc.2026.115036_bib92","article-title":"Graph attention guidance network with knowledge distillation for semantic segmentation of remote sensing images","volume":"61","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens"},{"issue":"12","key":"10.1016\/j.asoc.2026.115036_bib93","doi-asserted-by":"crossref","first-page":"7096","DOI":"10.1109\/TCSVT.2023.3275314","article-title":"MMSMCNet: Modal memory sharing and morphological complementary networks for RGB\u2013T urban scene semantic segmentation","volume":"33","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"4","key":"10.1016\/j.asoc.2026.115036_bib94","doi-asserted-by":"crossref","first-page":"3222","DOI":"10.1109\/TCSVT.2024.3508058","article-title":"MDNet: Mamba-effective diffusion-distillation network for RGB\u2013thermal urban dense prediction","volume":"35","author":"Zhou","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.asoc.2026.115036_bib95","series-title":"Proc","first-page":"12889","article-title":"Scaling local self-attention for parameter efficient visual backbones","author":"Vaswani","year":"2021"},{"key":"10.1016\/j.asoc.2026.115036_bib96","author":"Qiu","year":"2025","journal-title":"Gated Atten. Large Lang. Model. NonLinear sparsity Atten. SinkFree arXiv Prepr."},{"key":"10.1016\/j.asoc.2026.115036_bib97","doi-asserted-by":"crossref","unstructured":"Q.\u00a0Wang,\u00a0B.\u00a0Wu,\u00a0P.\u00a0Zhu,\u00a0P.\u00a0Li,\u00a0W.\u00a0Zuo,\u00a0Q.\u00a0Hu,\u00a0ECA-Net: Efficient channel attention for deep convolutional neural networks,\u00a0Proc,\u00a0IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Seattle, USA,\u00a02020, pp.\u00a011534\u201311542.","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"10.1016\/j.asoc.2026.115036_bib98","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2025.3627132","article-title":"GDROS: A geometry-guided dense registration framework for optical-SAR images under large geometric transformations","volume":"63","author":"Sun","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens"},{"key":"10.1016\/j.asoc.2026.115036_bib99","article-title":"Tuple perturbation-based contrastive learning framework for multimodal remote sensing image semantic segmentation","volume":"63","author":"Ye","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens"}],"container-title":["Applied Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626004849?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626004849?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T23:34:12Z","timestamp":1779579252000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1568494626004849"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":99,"alternative-id":["S1568494626004849"],"URL":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115036","relation":{},"ISSN":["1568-4946"],"issn-type":[{"value":"1568-4946","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"HaloSeg: Halo transformer embedding U-Net for local-global feature induced semantic segmentation of high-resolution remote sensing images","name":"articletitle","label":"Article Title"},{"value":"Applied Soft Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115036","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":"115036"}}