{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T08:28:36Z","timestamp":1793608116526,"version":"4.5.0"},"reference-count":34,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100017700","name":"Henan Provincial Science and Technology Research Project","doi-asserted-by":"publisher","award":["252102210019"],"award-info":[{"award-number":["252102210019"]}],"id":[{"id":"10.13039\/501100017700","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017700","name":"Henan Provincial Science and Technology Research Project","doi-asserted-by":"publisher","award":["262102211069"],"award-info":[{"award-number":["262102211069"]}],"id":[{"id":"10.13039\/501100017700","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017700","name":"Henan Provincial Science and Technology Research Project","doi-asserted-by":"publisher","award":["262102311248"],"award-info":[{"award-number":["262102311248"]}],"id":[{"id":"10.13039\/501100017700","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017278","name":"Nanyang Institute of Technology","doi-asserted-by":"publisher","award":["NGJC-2022-01"],"award-info":[{"award-number":["NGJC-2022-01"]}],"id":[{"id":"10.13039\/501100017278","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017278","name":"Nanyang Institute of Technology","doi-asserted-by":"publisher","award":["NGBJ-2023-32"],"award-info":[{"award-number":["NGBJ-2023-32"]}],"id":[{"id":"10.13039\/501100017278","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62502242"],"award-info":[{"award-number":["62502242"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2027,2]]},"DOI":"10.1016\/j.neunet.2026.109651","type":"journal-article","created":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T00:11:26Z","timestamp":1790035886000},"page":"109651","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["ALSRFormer: An adaptive transformer with dynamic window attention and multi-scale deformable feed-forward network for remote sensing image segmentation"],"prefix":"10.1016","volume":"206","author":[{"given":"Ziqi","family":"Jia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7452-8133","authenticated-orcid":false,"given":"Jiawei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3927-7616","authenticated-orcid":false,"given":"Dongen","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Penghua","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junze","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6564-6601","authenticated-orcid":false,"given":"Kaiyang","family":"Qu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109651_bib0001","series-title":"Proceedings of the European conference on computer vision (ECCV)","first-page":"801","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"Chen","year":"2018"},{"key":"10.1016\/j.neunet.2026.109651_bib0002","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S. et al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv: 2010.11929."},{"key":"10.1016\/j.neunet.2026.109651_bib0003","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1016\/j.isprsjprs.2021.11.005","article-title":"A coarse-to-fine boundary refinement network for building footprint extraction from remote sensing imagery","volume":"183","author":"Guo","year":"2022","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109651_bib0004","first-page":"1","article-title":"Swin transformer embedding UNet for remote sensing image semantic segmentation","volume":"60","author":"He","year":"2022","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109651_bib0005","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.neunet.2026.109651_bib0006","unstructured":"ISPRS (2022a). ISPRS test project on urban classification, 3D building reconstruction and semantic labeling\u2014Potsdam. https:\/\/www.isprs.org\/resources\/datasets\/benchmarks\/UrbanSemLab\/default.aspx. [EB\/OL]."},{"key":"10.1016\/j.neunet.2026.109651_bib0007","unstructured":"ISPRS (2022b). ISPRS test project on urban classification, 3D building reconstruction and semantic labeling\u2014Vaihingen. https:\/\/www.isprs.org\/resources\/datasets\/benchmarks\/UrbanSemLab\/default.aspx. [EB\/OL]."},{"issue":"1","key":"10.1016\/j.neunet.2026.109651_bib0008","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":"2018","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109651_bib0009","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"3","key":"10.1016\/j.neunet.2026.109651_bib0010","doi-asserted-by":"crossref","first-page":"1131","DOI":"10.1080\/01431161.2022.2030071","article-title":"A2-FPN for semantic segmentation of fine-resolution remotely sensed images","volume":"43","author":"Li","year":"2022","journal-title":"International Journal of Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109651_bib0011","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.neunet.2026.109651_bib0012","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"11976","article-title":"A convnet for the 2020s","author":"Liu","year":"2022"},{"key":"10.1016\/j.neunet.2026.109651_bib0013","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.neunet.2026.109651_bib0014","series-title":"2023 IEEE international conference on multimedia and expo (ICME)","first-page":"828","article-title":"Sacanet: Scene-aware class attention network for semantic segmentation of remote sensing images","author":"Ma","year":"2023"},{"key":"10.1016\/j.neunet.2026.109651_bib0015","first-page":"1","article-title":"Docnet: Dual-domain optimized class-aware network for remote sensing image segmentation","volume":"21","author":"Ma","year":"2024","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"key":"10.1016\/j.neunet.2026.109651_bib0016","article-title":"Logcan++: Adaptive local-global class-aware network for semantic segmentation of remote sensing images","author":"Ma","year":"2025","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109651_bib0017","doi-asserted-by":"crossref","unstructured":"Ma, X., Ma, M., Hu, C., Song, Z., Zhao, Z. S., Feng, T., & Zhang, W. (2023b). Log-CAN: Local-global class-aware network for semantic segmentation of remote sensing images. arXiv preprint arXiv: 2303.07747.","DOI":"10.1109\/ICASSP49357.2023.10095835"},{"key":"10.1016\/j.neunet.2026.109651_bib0018","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"367","article-title":"Conformer: Local features coupling global representations for visual recognition","author":"Peng","year":"2021"},{"key":"10.1016\/j.neunet.2026.109651_bib0019","first-page":"1","article-title":"Ugs-1m: Fine-grained urban green space mapping of 34 major cities in china based on the deep learning framework","volume":"2022","author":"Shi","year":"2022","journal-title":"Earth System Science Data Discussions"},{"key":"10.1016\/j.neunet.2026.109651_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.landurbplan.2019.05.011","article-title":"Monitoring finer-scale population density in urban functional zones: A remote sensing data fusion approach","volume":"190","author":"Song","year":"2019","journal-title":"Landscape and Urban Planning"},{"key":"10.1016\/j.neunet.2026.109651_bib0021","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109651_bib0022","unstructured":"Wang, J., Zheng, Z., Ma, A., Lu, X., & Zhong, Y. (2021a). LoveDA: A remote sensing land-cover dataset for domain adaptive semantic segmentation. arXiv preprint arXiv: 2110.08733."},{"key":"10.1016\/j.neunet.2026.109651_bib0023","first-page":"1","article-title":"Building extraction with vision transformer","volume":"60","author":"Wang","year":"2022","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109651_bib0024","first-page":"1","article-title":"A novel transformer based semantic segmentation scheme for fine-resolution remote sensing images","volume":"19","author":"Wang","year":"2022","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"issue":"16","key":"10.1016\/j.neunet.2026.109651_bib0025","doi-asserted-by":"crossref","first-page":"3065","DOI":"10.3390\/rs13163065","article-title":"Transformer meets convolution: A bilateral awareness network for semantic segmentation of very fine resolution urban scene images","volume":"13","author":"Wang","year":"2021","journal-title":"Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109651_bib0026","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 Journal of Photogrammetry and Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109651_bib0027","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"568","article-title":"Pyramid vision transformer: A versatile backbone for dense prediction without convolutions","author":"Wang","year":"2021"},{"key":"10.1016\/j.neunet.2026.109651_bib0028","doi-asserted-by":"crossref","DOI":"10.1016\/j.autcon.2019.102994","article-title":"Automated regional seismic damage assessment of buildings using an unmanned aerial vehicle and a convolutional neural network","volume":"109","author":"Xiong","year":"2020","journal-title":"Automation in Construction"},{"key":"10.1016\/j.neunet.2026.109651_bib0029","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5672","article-title":"Inceptionnext: When inception meets convnext","author":"Yu","year":"2024"},{"key":"10.1016\/j.neunet.2026.109651_bib0030","first-page":"1","article-title":"Three-dimension spatial\u2013spectral attention transformer for hyperspectral image denoising","volume":"62","author":"Zhang","year":"2024","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109651_bib0031","doi-asserted-by":"crossref","first-page":"6356","DOI":"10.1109\/TIP.2022.3211471","article-title":"Cooperated spectral low-rankness prior and deep spatial prior for HSI unsupervised denoising","volume":"31","author":"Zhang","year":"2022","journal-title":"IEEE Transactions on Image Processing"},{"issue":"10","key":"10.1016\/j.neunet.2026.109651_bib0032","doi-asserted-by":"crossref","first-page":"13143","DOI":"10.1109\/TNNLS.2023.3278866","article-title":"Hyperspectral image denoising: From model-driven, data-driven, to model-data-driven","volume":"35","author":"Zhang","year":"2023","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.109651_bib0033","first-page":"1","article-title":"Dsat-net: Dual spatial attention transformer for building extraction from aerial images","volume":"20","author":"Zhang","year":"2023","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"key":"10.1016\/j.neunet.2026.109651_bib0034","first-page":"1","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 Transactions on Geoscience and Remote Sensing"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026011068?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026011068?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T07:56:47Z","timestamp":1793606207000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026011068"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,2]]},"references-count":34,"alternative-id":["S0893608026011068"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109651","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"ALSRFormer: An adaptive transformer with dynamic window attention and multi-scale deformable feed-forward network for remote sensing image segmentation","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109651","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"109651"}}