{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T20:53:38Z","timestamp":1774558418655,"version":"3.50.1"},"reference-count":50,"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":[{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["2025J01297"],"award-info":[{"award-number":["2025J01297"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Technology Innovation Fund Project for SMEs","award":["202404AP110047"],"award-info":[{"award-number":["202404AP110047"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2025.3642913","type":"journal-article","created":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T18:46:30Z","timestamp":1765478790000},"page":"2132-2144","source":"Crossref","is-referenced-by-count":0,"title":["Seeing With Words: Interpretable Language-Guided Drone Geo-Localization via LLM-Enriched Semantic Attribute Alignment"],"prefix":"10.1109","volume":"28","author":[{"given":"Changsen","family":"Yuan","sequence":"first","affiliation":[{"name":"Beijing University of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9401-4432","authenticated-orcid":false,"given":"Yang-Hao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4546-3928","authenticated-orcid":false,"given":"Cunhan","family":"Guo","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2283-9089","authenticated-orcid":false,"given":"Danjie","family":"Han","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9296-9905","authenticated-orcid":false,"given":"Ge","family":"Shi","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8393-5703","authenticated-orcid":false,"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Electronic Engineering, University of Surrey, Guildford, U.K."}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.seta.2022.102558"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.281636"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341871"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3418097"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413896"},{"key":"ref6","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Jia","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110363"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00783"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73247-8_13"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01411"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3234822"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3371892"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3144066"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.440"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25457"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01545"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3346279"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249204"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32409"},{"key":"ref21","first-page":"27073","article-title":"Video2BEV: Transforming drone videos to BEVs for video-based geo-localization","author":"Ju","year":"2025"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1181"},{"key":"ref24","first-page":"3318","article-title":"Speaker-follower models for vision-and-language navigation","volume-title":"Proc. 32nd Conf. Neural Inf. Process. Syst.","author":"Fried","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00166"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref29","first-page":"652","article-title":"Landmark-RxR: Solving vision-and-language navigation with fine-grained alignment supervision","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst.","author":"He","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01374-3"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3051715"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_15"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103158"},{"key":"ref34","article-title":"Aerial vision-and-language navigation via semantic-topo-metric representation guided LLM reasoning","author":"Gao","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref38","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref39","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst.","volume":"34","author":"Li","year":"2021"},{"key":"ref40","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3393452"},{"key":"ref42","first-page":"25994","article-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Zeng","year":"2022"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611709"},{"key":"ref44","article-title":"Qwen2.5 technical report","author":"Yang","year":"2024"},{"key":"ref45","first-page":"640","article-title":"Data clustering by Markovian relaxation and the information bottleneck method","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tishby","year":"2000"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339661"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.24818\/ida-ql\/2019.5"},{"key":"ref50","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11297780.pdf?arnumber=11297780","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T19:51:01Z","timestamp":1774554661000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11297780\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3642913","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}