{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T04:06:37Z","timestamp":1746504397484,"version":"3.40.4"},"reference-count":49,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Key Laboratory of Target Cognition and Application Technology","award":["2023-CXPT-LC-005"],"award-info":[{"award-number":["2023-CXPT-LC-005"]}]},{"DOI":"10.13039\/501100002367","name":"Key Laboratory Fund of Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["CXJJ-23S032"],"award-info":[{"award-number":["CXJJ-23S032"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tgrs.2025.3562439","type":"journal-article","created":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T17:37:12Z","timestamp":1744997832000},"page":"1-15","source":"Crossref","is-referenced-by-count":0,"title":["Language-Guided Object Localization via Refined Spotting Enhancement in Remote Sensing Imagery"],"prefix":"10.1109","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4171-3234","authenticated-orcid":false,"given":"Peirong","family":"Zhang","sequence":"first","affiliation":[{"name":"Aerospace Information Research Institute, the Key Laboratory of Network Information System Technology (NIST), University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7466-0234","authenticated-orcid":false,"given":"Yidan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, the Key Laboratory of Network Information System Technology (NIST), University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Wu","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, the Key Laboratory of Network Information System Technology (NIST), University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1426-5056","authenticated-orcid":false,"given":"Xiaoxuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, the Key Laboratory of Network Information System Technology (NIST), University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingyan","family":"Hou","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, the Key Laboratory of Network Information System Technology (NIST), University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Wang","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, the Key Laboratory of Network Information System Technology (NIST), University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_29"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2016.03.014"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.11.023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2024.05.023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3250471"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548316"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00479"},{"key":"ref9","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref10","article-title":"GeoChat: Grounded large vision-language model for remote sensing","author":"Kuckreja","year":"2023","journal-title":"arXiv:2311.15826"},{"key":"ref11","article-title":"Shikra: Unleashing multimodal LLM\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv:2306.15195"},{"key":"ref12","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023","journal-title":"arXiv:2306.14824"},{"key":"ref13","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"},{"key":"ref14","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3241342"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3130443"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00832"},{"article-title":"Data-dependent Gaussian prior objective for language generation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2023.103540"},{"key":"ref20","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":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042066"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.333"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/155"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"ref28","first-page":"4252","article-title":"Parallel attention: A unified framework for visual object discovery through dialogs and queries","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Zhuang"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911066"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01661"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"ref35","first-page":"19652","article-title":"Referring transformer: A one-step approach to multi-task visual grounding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00928"},{"key":"ref37","article-title":"GPT4RoI: Instruction tuning large language model on region-of-interest","author":"Zhang","year":"2023","journal-title":"arXiv:2307.03601"},{"key":"ref38","article-title":"Pix2seq: A language modeling framework for object detection","author":"Chen","year":"2021","journal-title":"arXiv:2109.10852"},{"key":"ref39","first-page":"521","article-title":"UniTAB: Unifying text and box outputs for grounded vision-language modeling","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Yang"},{"key":"ref40","article-title":"NExT-chat: An LMM for chat, detection and segmentation","author":"Zhang","year":"2023","journal-title":"arXiv:2311.04498"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref44","article-title":"CrowdHuman: A benchmark for detecting human in a crowd","author":"Shao","year":"2018","journal-title":"arXiv:1805.00123"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3423663"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3407598"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7351502"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1804.02767"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10807682\/10970013.pdf?arnumber=10970013","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T17:55:53Z","timestamp":1746467753000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10970013\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2025.3562439","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"type":"print","value":"0196-2892"},{"type":"electronic","value":"1558-0644"}],"subject":[],"published":{"date-parts":[[2025]]}}}