{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T20:16:42Z","timestamp":1778271402283,"version":"3.51.4"},"reference-count":87,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"\u201cScientists + Engineers\u201d Project of Qin Chuangyuan in Shaanxi Province of China","award":["2024QCY-KXJ-152"],"award-info":[{"award-number":["2024QCY-KXJ-152"]}]},{"DOI":"10.13039\/501100013142","name":"Key Industry Chain Technology Research and Development General Project of Xi\u2019an","doi-asserted-by":"publisher","award":["2024JH-CLYB-0047"],"award-info":[{"award-number":["2024JH-CLYB-0047"]}],"id":[{"id":"10.13039\/501100013142","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"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["YJSJ26008"],"award-info":[{"award-number":["YJSJ26008"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62371373"],"award-info":[{"award-number":["62371373"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62271377"],"award-info":[{"award-number":["62271377"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62401418"],"award-info":[{"award-number":["62401418"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62501450"],"award-info":[{"award-number":["62501450"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3687442","type":"journal-article","created":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T19:38:26Z","timestamp":1777923506000},"page":"4816-4831","source":"Crossref","is-referenced-by-count":0,"title":["Scale-Aware Prompting With Optimal Transport for Remote Sensing Image Captioning"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0473-113X","authenticated-orcid":false,"given":"Cheng","family":"Zhang","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5425-6437","authenticated-orcid":false,"given":"Zhongle","family":"Ren","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, Xidian University, Xi’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, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7000-3325","authenticated-orcid":false,"given":"Jiawei","family":"Ning","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3226-8986","authenticated-orcid":false,"given":"Kai","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, Xidian University, Xi’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, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Licheng","family":"Jiao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3546853"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/mgrs.2025.3572702"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2024.3489613"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3539461"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3523305"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2025.3589096"},{"key":"ref7","article-title":"Towards vision-language geo-foundation model: A survey","author":"Zhou","year":"2024","journal-title":"arXiv:2406.09385"},{"key":"ref8","article-title":"A survey of large language model-powered spatial intelligence across scales: Advances in embodied agents, smart cities, and Earth science","author":"Feng","year":"2025","journal-title":"arXiv:2504.09848"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3502805"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/rs16214113"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3359316"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3401576"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1080\/17538947.2023.2283482"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3328181"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3305889"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3487846"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3385500"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3360089"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2025.3580686"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3413323"},{"key":"ref21","first-page":"1","article-title":"PLOT: Prompt learning with optimal transport for vision-language models","volume-title":"11th Proc. Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3475633"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3222606"},{"key":"ref24","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":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/PARC49193.2020.236619"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148210"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.130"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3617592"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3528216"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32517"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3177318"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref38","article-title":"ClipCap: CLIP prefix for image captioning","author":"Mokady","year":"2021","journal-title":"arXiv:2111.09734"},{"key":"ref39","article-title":"How much can CLIP benefit vision-and-language tasks?","author":"Shen","year":"2021","journal-title":"arXiv:2107.06383"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01746"},{"key":"ref41","volume-title":"M\u00e9moire Sur La Th\u00e9orie Des D\u00e9blais Et Des Remblais","author":"Monge","year":"1781"},{"issue":"2","key":"ref42","first-page":"227","article-title":"On the transfer of masses","volume":"37","author":"Kantorovich","year":"1942","journal-title":"Doklady Akademii Nauk"},{"key":"ref43","first-page":"8294","article-title":"Measuring generalization with optimal transport","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chuang"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00037"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_15"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3365248"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3531424"},{"key":"ref49","first-page":"1","article-title":"Bridging vision and language spaces with assignment prediction","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Park"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CITS.2016.7546397"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3150957"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2022.3201474"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.2980933"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2677464"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1080\/17538947.2024.2392847"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3198234"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3224244"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3510414"},{"key":"ref59","article-title":"A systematic survey of prompt engineering on vision-language foundation models","author":"Gu","year":"2023","journal-title":"arXiv:2307.12980"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref61","first-page":"1","article-title":"NV-embed: Improved techniques for training LLMs as generalist embedding models","volume-title":"Proc. 13th Proc. Int. Conf. Learn. Represent.","author":"Lee"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.299"},{"key":"ref63","first-page":"1","article-title":"TULIP: Token-length upgraded CLIP","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ivona"},{"key":"ref64","first-page":"2292","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Cuturi"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2929141"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.3390\/rs11060612"},{"key":"ref68","article-title":"Large language models for captioning and retrieving remote sensing images","author":"Daniel Silva","year":"2024","journal-title":"arXiv:2402.06475"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02249"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.3390\/electronics14142809"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02307"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3547988"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2025.113737"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3260825"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3350988"},{"key":"ref76","first-page":"1","article-title":"FILIP: Fine-grained interactive language-image pre-training","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yao"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01351"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1080\/01431161.2025.2575514"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.112209"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00052"},{"key":"ref81","first-page":"1","article-title":"Prompt learning with optimal transport for vision-language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01155"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32629"},{"key":"ref84","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref86","first-page":"1","article-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Li"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11503113.pdf?arnumber=11503113","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T19:43:03Z","timestamp":1778269383000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11503113\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":87,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3687442","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}