{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:36:09Z","timestamp":1777653369402,"version":"3.51.4"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171347"],"award-info":[{"award-number":["62171347"]}],"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":["62371373"],"award-info":[{"award-number":["62371373"]}],"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":["62401418"],"award-info":[{"award-number":["62401418"]}],"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":["62271377"],"award-info":[{"award-number":["62271377"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program in Shaanxi Province of China","award":["2024CY2-GJHX-17"],"award-info":[{"award-number":["2024CY2-GJHX-17"]}]},{"name":"Scientists + Engineers"},{"name":"Qin Chuangyuan in Shaanxi Province of China","award":["2024QCY-KXJ-152"],"award-info":[{"award-number":["2024QCY-KXJ-152"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/jstars.2025.3624411","type":"journal-article","created":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T17:51:59Z","timestamp":1761241919000},"page":"27208-27223","source":"Crossref","is-referenced-by-count":2,"title":["HATNet: Hierarchical Attention Transformer With RS-CLIP Patch Tokens for Remote Sensing Image Captioning"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5425-6437","authenticated-orcid":false,"given":"Zhongle","family":"Ren","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi&#x0027;an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Meng","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi&#x0027;an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0473-113X","authenticated-orcid":false,"given":"Cheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi&#x0027;an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9787-9495","authenticated-orcid":false,"given":"Shulin","family":"Gao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi&#x0027;an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1996-186X","authenticated-orcid":false,"given":"Biao","family":"Hou","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi&#x0027;an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0047-8955","authenticated-orcid":false,"given":"Weibin","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi&#x0027;an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4411-0933","authenticated-orcid":false,"given":"Hao","family":"Zhu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi&#x0027;an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3354-9617","authenticated-orcid":false,"given":"Licheng","family":"Jiao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi&#x0027;an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CITS.2016.7546397"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2017.8128075"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2677464"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2019.2893772"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS46834.2022.9883199"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/rs14122939"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3328181"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3359316"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3385500"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3426359"},{"key":"ref12","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00512"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/rs11202349"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2942154"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/rs12060939"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3198234"},{"key":"ref18","article-title":"RS5M: A large scale vision-language dataset for remote sensing vision-language foundation model","author":"Zhang","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4808"},{"key":"ref20","article-title":"How much can clip benefit vision-and-language tasks?","author":"Shen","year":"2021"},{"key":"ref21","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref23","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Karpathy","year":"2014"},{"key":"ref24","first-page":"220","article-title":"Composing simple image descriptions using web-scale n-grams","volume-title":"Proc. 15th Conf. Comput. Natural Lang. Learn.","author":"Li","year":"2011"},{"key":"ref25","first-page":"747","article-title":"Midge: Generating image descriptions from computer vision detections","volume-title":"Proc. 13th Conf. Eur. Ch. Assoc. Comput. Linguistics","author":"Mitchell","year":"2012"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref29","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren","year":"2015"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20160"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01062"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02237"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28203"},{"key":"ref36","article-title":"An image is worth 16  16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09294-7"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.105920"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3044054"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3153636"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3305889"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3510414"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018957"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3390\/rs11060612"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3070383"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3135711"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3102590"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3105004"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3201474"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3224244"},{"key":"ref51","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3401576"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2685945"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3150957"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"}],"container-title":["IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4609443\/10766875\/11214231.pdf?arnumber=11214231","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T05:54:16Z","timestamp":1762840456000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11214231\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/jstars.2025.3624411","relation":{},"ISSN":["1939-1404","2151-1535"],"issn-type":[{"value":"1939-1404","type":"print"},{"value":"2151-1535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}