{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T13:57:23Z","timestamp":1768571843271,"version":"3.49.0"},"reference-count":45,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tgrs.2025.3570895","type":"journal-article","created":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T13:44:18Z","timestamp":1747403058000},"page":"1-12","source":"Crossref","is-referenced-by-count":0,"title":["AirSpatialBot: A Spatially Aware Aerial Agent for Fine-Grained Vehicle Attribute Recognition and Retrieval"],"prefix":"10.1109","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3080-6721","authenticated-orcid":false,"given":"Yue","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Information Science and Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ran","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Information Science and Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7084-9101","authenticated-orcid":false,"given":"Xue","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7099-6817","authenticated-orcid":false,"given":"Xue","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Information Science and Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4533-3904","authenticated-orcid":false,"given":"Xingzhao","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information Science and Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Thinking in space: How multimodal large language models see, remember, and recall spaces","author":"Yang","year":"2024","journal-title":"arXiv:2412.14171"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/Ucom62433.2024.10695912"},{"key":"ref3","article-title":"Towards realistic UAV vision-language navigation: Platform, benchmark, and methodology","author":"Wang","year":"2024","journal-title":"arXiv:2410.07087"},{"key":"ref4","article-title":"Towards vision-language geo-foundation model: A survey","author":"Zhou","year":"2024","journal-title":"arXiv:2406.09385"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042066"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref7","article-title":"Open3D: A modern library for 3D data processing","author":"Zhou","year":"2018","journal-title":"arXiv:1801.09847"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548316"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3250471"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00055"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01600"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3407598"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3423663"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02629"},{"key":"ref15","article-title":"VRSBench: A versatile vision-language benchmark dataset for remote sensing image understanding","author":"Li","year":"2024","journal-title":"arXiv:2406.12384"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3132095"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3102590"},{"key":"ref18","article-title":"Deep unsupervised contrastive hashing for large-scale cross-modal text-image retrieval in remote sensing","author":"Mikriukov","year":"2022","journal-title":"arXiv:2201.08125"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2988782"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3079918"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3312479"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3090981"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3203314"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28357"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS47720.2021.9553307"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1080\/01431161.2022.2145583"},{"key":"ref27","article-title":"RSGPT: A remote sensing vision language model and benchmark","author":"Hu","year":"2023","journal-title":"arXiv:2307.15266"},{"key":"ref28","article-title":"SpatialBot: Precise spatial understanding with vision language models","author":"Cai","year":"2024","journal-title":"arXiv:2406.13642"},{"key":"ref29","article-title":"OmniDrive: A holistic vision-language dataset for autonomous driving with counterfactual reasoning","author":"Wang","year":"2024","journal-title":"arXiv:2405.01533"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72904-1_26"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32683"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3409624"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00418"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.11.023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.19"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3197152"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_48"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3119563"},{"key":"ref39","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv:2304.08485"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.12.004"},{"key":"ref41","article-title":"InternVL: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","author":"Chen","year":"2023","journal-title":"arXiv:2312.14238"},{"key":"ref42","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv:2308.12966"},{"key":"ref43","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv:2409.12191"},{"key":"ref44","article-title":"REO-VLM: Transforming VLM to meet regression challenges in Earth observation","author":"Xue","year":"2024","journal-title":"arXiv:2412.16583"},{"key":"ref45","article-title":"DeepSeek-V3 technical report","volume-title":"arXiv:2412.19437","year":"2024"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10807682\/11006099.pdf?arnumber=11006099","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:49:48Z","timestamp":1768510188000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11006099\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2025.3570895","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}