{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:39:54Z","timestamp":1783183194896,"version":"3.54.6"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171327"],"award-info":[{"award-number":["62171327"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"First Batch of Application Basic Technology and Science Research Foundation in Hubei Nuclear Power Operation Engineering Technology Research Center","award":["B210610"],"award-info":[{"award-number":["B210610"]}]},{"name":"Hubei Provincial Natural Science Foundation of China","award":["2022CFCO31"],"award-info":[{"award-number":["2022CFCO31"]}]},{"name":"Hubei Provincial Natural Science Foundation of China","award":["2023AFA035"],"award-info":[{"award-number":["2023AFA035"]}]},{"DOI":"10.13039\/501100013064","name":"Key Research and Development Program in Hubei Province, China","doi-asserted-by":"publisher","award":["2022BAA079"],"award-info":[{"award-number":["2022BAA079"]}],"id":[{"id":"10.13039\/501100013064","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tgrs.2024.3487576","type":"journal-article","created":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T17:31:37Z","timestamp":1730223097000},"page":"1-16","source":"Crossref","is-referenced-by-count":15,"title":["SegCLIP: Multimodal Visual-Language and Prompt Learning for High-Resolution Remote Sensing Semantic Segmentation"],"prefix":"10.1109","volume":"62","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8939-4025","authenticated-orcid":false,"given":"Shijie","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology and Hubei Province Key Laboratory of Intelligent Robots, Wuhan Institute of Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2190-6253","authenticated-orcid":false,"given":"Bin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology and Hubei Province Key Laboratory of Intelligent Robots, Wuhan Institute of Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7911-4104","authenticated-orcid":false,"given":"Yuntao","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology and Hubei Province Key Laboratory of Intelligent Robots, Wuhan Institute of Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5007-7303","authenticated-orcid":false,"given":"Huabing","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology and Hubei Province Key Laboratory of Intelligent Robots, Wuhan Institute of Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5694-505X","authenticated-orcid":false,"given":"Junjun","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3264-3265","authenticated-orcid":false,"given":"Jiayi","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Electronic Information, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114417"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196722"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2017.8258373"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3109728"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2022.05.007"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.103207"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.bdr.2021.100295"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2017.02.003"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3140108"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2020.2980210"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3053062"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.01270"},{"key":"ref16","first-page":"15","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref20","article-title":"Swin-Unet: Unet-like pure transformer for medical image segmentation","author":"Cao","year":"2021","journal-title":"arXiv:2105.05537"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3178991"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3256064"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3385318"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3302024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2022.06.008"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2023.3238648"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3314641"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/rs15204987"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3390\/rs10050743"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS47720.2021.9555029"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3165209"},{"key":"ref33","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Harold Li","year":"2019","journal-title":"arXiv:1908.03557"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/jstars.2022.3215803"},{"key":"ref35","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2024.01.004"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS53475.2024.10642152"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.07.016"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref43","first-page":"1","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref45","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Cheng"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_17"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3289408"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3292919"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3406867"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2021.3129609"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108695"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_41"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref59","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"issue":"8","key":"ref60","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3233885"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3132189"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3250448"},{"key":"ref64","first-page":"1","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lu"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref66","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li"},{"key":"ref67","article-title":"WenLan: Bridging vision and language by large-scale multi-modal pre-training","author":"Huo","year":"2021","journal-title":"arXiv:2103.06561"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00088"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw59228.2023.00196"},{"key":"ref70","article-title":"LoveDA: A remote sensing land-cover dataset for domain adaptive semantic segmentation","author":"Wang","year":"2021","journal-title":"arXiv:2110.08733"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref73","first-page":"28","article-title":"ISAID: A large-scale dataset for instance segmentation in aerial images","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR) Workshop","author":"Zamir"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.05.009"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_11"},{"key":"ref76","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Sys. (NIPS)","volume":"34","author":"Xie"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01733"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10354519\/10737389.pdf?arnumber=10737389","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T17:32:21Z","timestamp":1747243941000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10737389\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2024.3487576","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}