{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T09:15:25Z","timestamp":1783156525903,"version":"3.54.6"},"reference-count":56,"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","id":[{"id":"10.13039\/501100001809","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":[[2026,8]]},"DOI":"10.1016\/j.asoc.2026.115430","type":"journal-article","created":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T22:23:11Z","timestamp":1778970191000},"page":"115430","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["DSFNet: A dual-stream feature fusion network based on strip convolution and transformer for building extraction"],"prefix":"10.1016","volume":"200","author":[{"given":"Peng","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiuqiao","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianga","family":"Shang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yishi","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.asoc.2026.115430_bib0005","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"SegNet: a deep convolutional encoder-decoder architecture for image segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.asoc.2026.115430_bib0010","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"27706","article-title":"Poly kernel inception network for remote sensing detection","author":"Cai","year":"2024"},{"key":"10.1016\/j.asoc.2026.115430_bib0015","series-title":"European Conference on Computer Vision","first-page":"205","article-title":"Swin-Unet: Unet-like pure transformer for medical image segmentation","author":"Cao","year":"2022"},{"key":"10.1016\/j.asoc.2026.115430_bib0020","doi-asserted-by":"crossref","first-page":"1010","DOI":"10.3390\/s24031010","article-title":"Multi-scale attention network for building extraction from high-resolution remote sensing images","volume":"24","author":"Chang","year":"2024","journal-title":"Sensors"},{"key":"10.1016\/j.asoc.2026.115430_bib0025","doi-asserted-by":"crossref","first-page":"16577","DOI":"10.1109\/JSTARS.2024.3452640","article-title":"Depth feature fusion network for building extraction in remote sensing images","volume":"17","author":"Chen","year":"2024","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0030","doi-asserted-by":"crossref","first-page":"4441","DOI":"10.3390\/rs13214441","article-title":"Building extraction from remote sensing images with sparse token transformers","volume":"13","author":"Chen","year":"2021","journal-title":"Remote. Sens."},{"key":"10.1016\/j.asoc.2026.115430_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.asoc.2026.115430_bib0040","series-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"1","article-title":"Xception: deep learning with depthwise separable convolutions","author":"Chollet","year":"2017"},{"key":"10.1016\/j.asoc.2026.115430_bib0045","doi-asserted-by":"crossref","first-page":"22094","DOI":"10.1109\/JSTARS.2025.3600243","article-title":"Edge information extraction based open-set airplane detection in remote sensing images","volume":"18","author":"Dang","year":"2025","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0050","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.asoc.2026.115430_bib0055","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12124","article-title":"CSWin transformer: a general vision transformer backbone with cross-shaped windows","author":"Dong","year":"2022"},{"key":"10.1016\/j.asoc.2026.115430_bib0060","author":"Dosovitskiy"},{"key":"10.1016\/j.asoc.2026.115430_bib0065","doi-asserted-by":"crossref","first-page":"327","DOI":"10.3390\/rs16020327","article-title":"Remote sensing object detection in the deep learning era\u2014a review","volume":"16","author":"Gui","year":"2024","journal-title":"Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0070","first-page":"1","article-title":"Edge-guided remote-sensing image compression","volume":"61","author":"Han","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0075","doi-asserted-by":"crossref","first-page":"4490","DOI":"10.1109\/JSTARS.2021.3073935","article-title":"Attention-guided label refinement network for semantic segmentation of very high resolution aerial orthoimages","volume":"14","author":"Huang","year":"2021","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0080","first-page":"3121","article-title":"LightViT: towards light-weight transformer for remote sensing image segmentation","volume":"14","author":"Huang","year":"2022","journal-title":"Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0085","doi-asserted-by":"crossref","first-page":"4112","DOI":"10.3390\/rs15164112","article-title":"A review of practical AI for remote sensing in earth sciences","volume":"15","author":"Janga","year":"2023","journal-title":"Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0090","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1109\/TGRS.2018.2858817","article-title":"Fully convolutional networks for multisource building extraction from an open aerial and satellite imagery data set","volume":"57","author":"Ji","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0095","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.asoc.2026.115430_bib0100","first-page":"1","article-title":"Lightweight salient object detection in optical remote-sensing images via semantic matching and edge alignment","volume":"61","author":"Li","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0105","article-title":"A review of building extraction from remote sensing imagery: geometrical structures and semantic attributes","volume":"62","author":"Li","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0110","first-page":"1","article-title":"A synergistical attention model for semantic segmentation of remote sensing images","volume":"61","author":"Li","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0115","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.isprsjprs.2024.01.022","article-title":"HD-Net: high-resolution decoupled network for building footprint extraction via deeply supervised body and boundary decomposition","volume":"209","author":"Li","year":"2024","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0120","first-page":"1","article-title":"LSKNet: a foundation lightweight backbone for remote sensing","author":"Li","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.asoc.2026.115430_bib0125","first-page":"1","article-title":"Recurrent attention and semantic gate for remote sensing image captioning","volume":"60","author":"Li","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0130","article-title":"MDFA-Net: multi-scale differential feature self-attention network for building change detection in remote sensing images","volume":"16","author":"Li","year":"2024","journal-title":"Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0135","first-page":"1","article-title":"Rethinking transformers for semantic segmentation of remote sensing images","volume":"61","author":"Liu","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0140","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10012","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.asoc.2026.115430_bib0145","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3431","article-title":"Fully convolutional networks for semantic segmentation","author":"Long","year":"2015"},{"key":"10.1016\/j.asoc.2026.115430_bib0150","series-title":"IEEE International Geoscience and Remote Sensing Symposium (IGARSS)","article-title":"Can semantic labeling methods generalize to any city? The inria aerial image labeling benchmark","author":"Maggiori","year":"2017"},{"key":"10.1016\/j.asoc.2026.115430_bib0155","series-title":"Machine learning for aerial image labeling","author":"Mnih","year":"2013"},{"key":"10.1016\/j.asoc.2026.115430_bib0160","doi-asserted-by":"crossref","first-page":"8461","DOI":"10.1109\/JSTARS.2024.3387969","article-title":"MDCGA-Net: multi-scale direction context-aware network with global attention for building extraction from remote sensing images","volume":"17","author":"Niu","year":"2024","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0165","doi-asserted-by":"crossref","DOI":"10.1080\/15481603.2025.2536903","article-title":"WaveFuseNet: a multiscale wavelet-transform convolutional network with adaptive feature fusion for building extraction","volume":"62","author":"Qiu","year":"2025","journal-title":"Giscience Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0170","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"},{"key":"10.1016\/j.asoc.2026.115430_bib0175","series-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"5686","article-title":"Deep high-resolution representation learning for human pose estimation","author":"Sun","year":"2019"},{"key":"10.1016\/j.asoc.2026.115430_bib0180","series-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"2818","article-title":"Rethinking the inception architecture for computer vision","author":"Szegedy","year":"2015"},{"key":"10.1016\/j.asoc.2026.115430_bib0185","series-title":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"1","article-title":"Going deeper with convolutions","author":"Szegedy","year":"2014"},{"key":"10.1016\/j.asoc.2026.115430_bib0190","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.asoc.2026.115430_bib0195","first-page":"4415","article-title":"Buildformer: a transformer-based network for building extraction from remote sensing images","volume":"13","author":"Wang","year":"2021","journal-title":"Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0200","first-page":"4415","article-title":"HybridViT: hierarchical vision transformer with local and global representations for remote sensing image segmentation","volume":"15","author":"Wang","year":"2023","journal-title":"Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0205","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1007\/s41095-022-0274-8","article-title":"PVT v2: improved baselines with pyramid vision transformer","volume":"8","author":"Wang","year":"2022","journal-title":"Comput. Vis. Media"},{"key":"10.1016\/j.asoc.2026.115430_bib0210","doi-asserted-by":"crossref","first-page":"951","DOI":"10.1109\/JSTARS.2020.3043442","article-title":"Boundary-aware multitask learning for remote sensing imagery","volume":"14","author":"Wang","year":"2021","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0215","doi-asserted-by":"crossref","first-page":"10368","DOI":"10.1109\/JSTARS.2024.3400925","article-title":"Bitemporal attention sharing network for remote sensing image change detection","volume":"17","author":"Wang","year":"2024","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0220","doi-asserted-by":"crossref","first-page":"927","DOI":"10.3390\/rs15040927","article-title":"A multi-scale edge constraint network for the fine extraction of buildings from remote sensing images","volume":"15","author":"Wang","year":"2023","journal-title":"Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0225","first-page":"1","article-title":"Transmin: transformer-guided multi-interaction network for remote sensing object detection","volume":"20","author":"Xu","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"10.1016\/j.asoc.2026.115430_bib0230","first-page":"1","article-title":"Bctnet: bi-branch cross-fusion transformer for building footprint extraction","volume":"61","author":"Xu","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0235","doi-asserted-by":"crossref","first-page":"3585","DOI":"10.3390\/rs13183585","article-title":"Efficient transformer for remote sensing image segmentation","volume":"13","author":"Xu","year":"2021","journal-title":"Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0240","first-page":"1","article-title":"RingMo-SAM: a foundation model for segment anything in multimodal remote-sensing images","volume":"61","author":"Yan","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0245","author":"Yuan"},{"key":"10.1016\/j.asoc.2026.115430_bib0250","doi-asserted-by":"crossref","first-page":"1269","DOI":"10.1109\/TNNLS.2020.3041646","article-title":"A local\u2013global dual-stream network for building extraction from very-high-resolution remote sensing images","volume":"33","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.asoc.2026.115430_bib0255","first-page":"3121","article-title":"E2EC: end-to-end context encoding for remote sensing image segmentation","volume":"14","author":"Zhang","year":"2022","journal-title":"Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0260","first-page":"1","article-title":"HiT: building mapping with hierarchical transformers","volume":"62","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0265","series-title":"IEEE Geoscience and Remote Sensing Letters","first-page":"1","article-title":"SDSC-UNet: dual skip connection ViT-based U-shaped model for building extraction","volume":"vol. 20","author":"Zhang","year":"2023"},{"key":"10.1016\/j.asoc.2026.115430_bib0270","article-title":"LSRFormer: efficient transformer supply convolutional neural networks with global information for aerial image segmentation","volume":"62","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.asoc.2026.115430_bib0275","first-page":"1","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."},{"key":"10.1016\/j.asoc.2026.115430_bib0280","first-page":"1","article-title":"BOMSC-Net: boundary optimization and multi-scale context awareness based building extraction from high-resolution remote sensing imagery","volume":"60","author":"Zhou","year":"2022","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:S1568494626008781?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626008781?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T08:20:09Z","timestamp":1783153209000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1568494626008781"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":56,"alternative-id":["S1568494626008781"],"URL":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115430","relation":{},"ISSN":["1568-4946"],"issn-type":[{"value":"1568-4946","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"DSFNet: A dual-stream feature fusion network based on strip convolution and transformer for building extraction","name":"articletitle","label":"Article Title"},{"value":"Applied Soft Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115430","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":"115430"}}