{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T15:02:25Z","timestamp":1784041345840,"version":"3.55.0"},"reference-count":51,"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":["62376283"],"award-info":[{"award-number":["62376283"]}],"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":["62531026"],"award-info":[{"award-number":["62531026"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"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.2025.3616330","type":"journal-article","created":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T17:39:21Z","timestamp":1759340361000},"page":"26586-26598","source":"Crossref","is-referenced-by-count":1,"title":["Could Describe Anything Model Understand Remote Sensing Objects?"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9262-8332","authenticated-orcid":false,"given":"Ziyi","family":"Gao","sequence":"first","affiliation":[{"name":"College of Electronic Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8453-3346","authenticated-orcid":false,"given":"Shuzhou","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Computer Science & Technology, Institute for AI, BNRist Center, THBI Lab, Tsinghua-Bosch Joint Center for ML, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5550-8758","authenticated-orcid":false,"given":"Ming-Ming","family":"Cheng","sequence":"additional","affiliation":[{"name":"TKLNDST, College of Computer Science, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6095-5965","authenticated-orcid":false,"given":"Yunli","family":"Long","sequence":"additional","affiliation":[{"name":"College of Electronic Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongxiang","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Electronic Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2011-2873","authenticated-orcid":false,"given":"Li","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Electronic Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3150957"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3548664"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2025.03.028"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2025.3603036"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3537283"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3568644"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3409624"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02613"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3386020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3383649"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3574657"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3531988"},{"key":"ref16","article-title":"Describe anything: Detailed localized image and video captioning","author":"Lian","year":"2025"},{"key":"ref17","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":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3390838"},{"key":"ref19","article-title":"Set-of-mark prompting unleashes extraordinary visual grounding in GPT-4v","author":"Yang","year":"2023"},{"key":"ref20","article-title":"Shikra: Unleashing multimodal LLMS referential dialogue magic","author":"Chen","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01309"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01273"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01237"},{"key":"ref25","article-title":"Caption anything: Interactive image description with diverse multimodal controls","author":"Wang","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72920-1_2"},{"key":"ref27","first-page":"359","article-title":"Collective generation of natural image descriptions","volume-title":"Proc. 50th Annu. Meeting Assoc. Comput. Linguistics","author":"Kuznetsova","year":"2012"},{"key":"ref28","first-page":"1","article-title":"Sequence to sequence learning with neural networks","volume":"27","author":"Sutskever","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2019.2893772"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34500-5_24"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2677464"},{"key":"ref33","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref36","article-title":"Recurrent neural network regularization","author":"Zaremba","year":"2014"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"ref38","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref39","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":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3610039"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3718362"},{"key":"ref42","article-title":"Describe Anything Model for Visual Question Answering on Text-rich Images","author":"Vu","year":"2025"},{"key":"ref43","article-title":"Describe anything in medical images","author":"Xiao","year":"2025"},{"key":"ref44","article-title":"SAM2: Segment anything in images and videos","author":"Ravi","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2015.303"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3390\/rs14215460"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3390\/rs13183690"},{"key":"ref49","article-title":"Infrared maritime ship dataset","author":"Li","year":"2025"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2025.3570697"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2024.12.011"}],"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\/11185294.pdf?arnumber=11185294","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T17:36:18Z","timestamp":1761759378000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11185294\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/jstars.2025.3616330","relation":{},"ISSN":["1939-1404","2151-1535"],"issn-type":[{"value":"1939-1404","type":"print"},{"value":"2151-1535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}