{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T16:32:49Z","timestamp":1792600369280,"version":"4.5.0"},"reference-count":40,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"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":["Pattern Recognition"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.patcog.2026.113120","type":"journal-article","created":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T00:15:28Z","timestamp":1769213728000},"page":"113120","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":7,"special_numbering":"C","title":["Towards open-vocabulary semantic segmentation for remote sensing images"],"prefix":"10.1016","volume":"175","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9248-2941","authenticated-orcid":false,"given":"Da","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2335-5421","authenticated-orcid":false,"given":"Mingmin","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2924-946X","authenticated-orcid":false,"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113120_bib0001","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111503","article-title":"Progressive class-aware instance enhancement for aircraft detection in remote sensing imagery","volume":"164","author":"Shi","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113120_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111895","article-title":"Fully polsar image reconstruction for enhanced land cover mapping","volume":"169","author":"Sun","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113120_bib0003","first-page":"1","article-title":"A novel framework for urban land cover change detection with Nasa\u2019s black marble nighttime lights product","volume":"61","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113120_bib0004","doi-asserted-by":"crossref","unstructured":"D. Zhang, F. Wang, L. Ning, Z. Zhao, J. Gao, X. Li, Integrating sam with feature interaction for remote sensing change detection, 2024.","DOI":"10.1109\/TGRS.2024.3483775"},{"key":"10.1016\/j.patcog.2026.113120_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.rse.2021.112636","article-title":"Building damage assessment for rapid disaster response with a deep object-based semantic change detection framework: from natural disasters to man-made disasters","volume":"265","author":"Zheng","year":"2021","journal-title":"Remote Sens. Environ."},{"issue":"23","key":"10.1016\/j.patcog.2026.113120_bib0006","doi-asserted-by":"crossref","first-page":"4902","DOI":"10.3390\/rs13234902","article-title":"SDFCNv2: an improved fcn framework for remote sensing images semantic segmentation","volume":"13","author":"Chen","year":"2021","journal-title":"Remote Sens."},{"issue":"4","key":"10.1016\/j.patcog.2026.113120_bib0007","doi-asserted-by":"crossref","DOI":"10.1007\/s11432-019-2791-7","article-title":"Hybrid first and second order attention Unet for building segmentation in remote sensing images","volume":"63","author":"He","year":"2020","journal-title":"Sci. China Inf. Sci."},{"issue":"18","key":"10.1016\/j.patcog.2026.113120_bib0008","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.patcog.2026.113120_bib0009","doi-asserted-by":"crossref","unstructured":"Z. Wang, H. Chang, L. Bai, L. Chen, X. Bi, A creative weak supervised semantic segmentation for remote sensing images, 2024.","DOI":"10.1109\/TGRS.2024.3477749"},{"key":"10.1016\/j.patcog.2026.113120_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111661","article-title":"Separation of unknown features and samples for unbiased source-free open set domain adaptation","volume":"166","author":"Li","year":"2025","journal-title":"Pattern Recognit."},{"issue":"2","key":"10.1016\/j.patcog.2026.113120_bib0011","doi-asserted-by":"crossref","first-page":"290","DOI":"10.3390\/rs17020290","article-title":"Hierarchical transfer learning with transformers to improve semantic segmentation in remote sensing land use","volume":"17","author":"Chen","year":"2025","journal-title":"Remote Sens."},{"key":"10.1016\/j.patcog.2026.113120_bib0012","doi-asserted-by":"crossref","unstructured":"Q. Cao, Y. Chen, C. Ma, X. Yang, Open-vocabulary high-resolution remote sensing image semantic segmentation, 2025.","DOI":"10.1109\/TGRS.2025.3559557"},{"issue":"8","key":"10.1016\/j.patcog.2026.113120_bib0013","doi-asserted-by":"crossref","first-page":"1357","DOI":"10.3390\/rs17081357","article-title":"Open-vocabulary domain generalization of remote-sensing images for semantic segmentation","volume":"17","author":"Wu","year":"2025","journal-title":"Remote Sens."},{"issue":"20","key":"10.1016\/j.patcog.2026.113120_bib0014","doi-asserted-by":"crossref","first-page":"4987","DOI":"10.3390\/rs15204987","article-title":"Deep learning methods for semantic segmentation in remote sensing with small data: a survey","volume":"15","author":"Yu","year":"2023","journal-title":"Remote Sens."},{"key":"10.1016\/j.patcog.2026.113120_bib0015","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7061","article-title":"Open-vocabulary semantic segmentation with mask-adapted clip","author":"Liang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113120_bib0016","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4113","article-title":"CAT-Seg: cost aggregation for open-vocabulary semantic segmentation","author":"Cho","year":"2024"},{"issue":"8","key":"10.1016\/j.patcog.2026.113120_bib0017","doi-asserted-by":"crossref","first-page":"5625","DOI":"10.1109\/TPAMI.2024.3369699","article-title":"Vision-language models for vision tasks: a survey","volume":"46","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113120_bib0018","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"10545","article-title":"SegEarth-OV: towards training-free open-vocabulary segmentation for remote sensing images","author":"Li","year":"2025"},{"key":"10.1016\/j.patcog.2026.113120_bib0019","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"2254","article-title":"AeroSeg: harnessing sam for open-vocabulary segmentation in remote sensing images","author":"Dutta","year":"2025"},{"key":"10.1016\/j.patcog.2026.113120_bib0020","first-page":"9436","article-title":"Towards open-vocabulary remote sensing image semantic segmentation","volume":"39","author":"Ye","year":"2025","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.patcog.2026.113120_bib0021","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3426","article-title":"A simple encoder-decoder for open-vocabulary semantic segmentation","author":"Xie","year":"2024"},{"key":"10.1016\/j.patcog.2026.113120_bib0022","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. Photogramm. Remote Sens."},{"issue":"12","key":"10.1016\/j.patcog.2026.113120_bib0023","doi-asserted-by":"crossref","first-page":"2077","DOI":"10.3390\/rs16122077","article-title":"U-Net ensemble for enhanced semantic segmentation in remote sensing imagery","volume":"16","author":"Dimitrovski","year":"2024","journal-title":"Remote Sens."},{"key":"10.1016\/j.patcog.2026.113120_bib0024","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, An image is worth 16\u202f\u202f\u00d7\u202f\u202f16 words: transformers for image recognition at scale, Technical Report, arXiv: 2010.11929, 2020."},{"issue":"6","key":"10.1016\/j.patcog.2026.113120_bib0025","doi-asserted-by":"crossref","first-page":"3660","DOI":"10.1109\/TGRS.2016.2523563","article-title":"Semantic annotation of high-resolution satellite images via weakly supervised learning","volume":"54","author":"Yao","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113120_bib0026","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/j.isprsjprs.2020.05.009","article-title":"Uavid: a semantic segmentation dataset for uav imagery","volume":"165","author":"Lyu","year":"2020","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113120_bib0027","first-page":"1","article-title":"Semantic segmentation of remote sensing images with sparse annotations","volume":"19","author":"Hua","year":"2021","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"10.1016\/j.patcog.2026.113120_bib0028","first-page":"1","article-title":"Semisupervised semantic segmentation of remote sensing images with consistency self-training","volume":"60","author":"Li","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113120_bib0029","doi-asserted-by":"crossref","unstructured":"Y. Jia, W. Fu, J. Gao, Q. Wang, Dual-view classifier evolution for generalized remote sensing few-shot segmentation, 2025.","DOI":"10.1109\/TGRS.2025.3555209"},{"key":"10.1016\/j.patcog.2026.113120_bib0030","first-page":"1","article-title":"Unsupervised domain adaptation semantic segmentation of high-resolution remote sensing imagery with invariant domain-level prototype memory","volume":"61","author":"Zhu","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113120_bib0031","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.patcog.2026.113120_bib0032","series-title":"Technical Report","article-title":"Language-Driven Semantic Segmentation","author":"Li","year":"2022"},{"key":"10.1016\/j.patcog.2026.113120_bib0033","series-title":"Scaling Open-Vocabulary Image Segmentation with Image-Level Labels","author":"Ghiasi","year":"2022"},{"key":"10.1016\/j.patcog.2026.113120_bib0034","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19446","article-title":"FreeSeg: unified, universal and open-vocabulary image segmentation","author":"Qin","year":"2023"},{"key":"10.1016\/j.patcog.2026.113120_bib0035","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2945","article-title":"Side adapter network for open-vocabulary semantic segmentation","author":"Xu","year":"2023"},{"key":"10.1016\/j.patcog.2026.113120_bib0036","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3491","article-title":"Open-vocabulary segmentation with semantic-assisted calibration","author":"Liu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113120_bib0037","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"797","article-title":"Global knowledge calibration for fast open-vocabulary segmentation","author":"Han","year":"2023"},{"key":"10.1016\/j.patcog.2026.113120_bib0038","first-page":"1","article-title":"Scale-aware detailed matching for few-shot aerial image semantic segmentation","volume":"60","author":"Yao","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"2","key":"10.1016\/j.patcog.2026.113120_bib0039","doi-asserted-by":"crossref","first-page":"1144","DOI":"10.1109\/TGRS.2017.2760909","article-title":"Multilabel remote sensing image retrieval using a semisupervised graph-theoretic method","volume":"56","author":"Chaudhuri","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"12","key":"10.1016\/j.patcog.2026.113120_bib0040","doi-asserted-by":"crossref","first-page":"8954","DOI":"10.1109\/TPAMI.2024.3413013","article-title":"A survey on open-vocabulary detection and segmentation: past, present, and future","volume":"46","author":"Zhu","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S003132032600083X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S003132032600083X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T17:09:46Z","timestamp":1788282586000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S003132032600083X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":40,"alternative-id":["S003132032600083X"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113120","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Towards open-vocabulary semantic segmentation for remote sensing images","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113120","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":"113120"}}