{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T00:17:10Z","timestamp":1755217030798,"version":"3.43.0"},"reference-count":22,"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":"National Key R&D Program of China","award":["2022ZD0160601"],"award-info":[{"award-number":["2022ZD0160601"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306315"],"award-info":[{"award-number":["62306315"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/lsp.2025.3585831","type":"journal-article","created":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T13:31:20Z","timestamp":1751549480000},"page":"2853-2857","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Visual Aligning and Grounding for Aerial Vision-and-Dialog Navigation"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0014-2550","authenticated-orcid":false,"given":"Guanhui","family":"Qiao","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1282-7310","authenticated-orcid":false,"given":"Dong","family":"Yi","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9346-3597","authenticated-orcid":false,"given":"Lingxiang","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanxiao","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9118-2780","authenticated-orcid":false,"given":"Jinqiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3346207"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3423663"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.190"},{"article-title":"Target-grounded graph-aware transformer for aerial vision-and-dialog navigation","year":"2023","author":"Su","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01433"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref9","first-page":"394","article-title":"Vision-and-dialog navigation","volume-title":"Proc. Mach. Learn. Res.","author":"Thomason","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01250"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"article-title":"Robust cross-view geo-localization via content-viewpoint disentanglement","year":"2025","author":"Li","key":"ref12"},{"article-title":"Vl-bert: Pre-training of generic visual-linguistic representations","year":"2019","author":"Su","key":"ref13"},{"key":"ref14","first-page":"13","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"article-title":"Visualbert: A simple and performant baseline for vision and language","year":"2019","author":"Li","key":"ref15"},{"article-title":"Xview: Objects in context in overhead imagery","year":"2018","author":"Lam","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32758"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"article-title":"Roberta: A robustly optimized Bert pretraining approach","year":"2019","author":"Liu","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3344374"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.264"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/10802935\/11067948.pdf?arnumber=11067948","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T04:40:59Z","timestamp":1754368859000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11067948\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/lsp.2025.3585831","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"type":"print","value":"1070-9908"},{"type":"electronic","value":"1558-2361"}],"subject":[],"published":{"date-parts":[[2025]]}}}