{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T17:44:59Z","timestamp":1755798299732,"version":"3.44.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,14]],"date-time":"2025-09-14T00:00:00Z","timestamp":1757808000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,14]],"date-time":"2025-09-14T00:00:00Z","timestamp":1757808000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,14]]},"DOI":"10.1109\/icip55913.2025.11084696","type":"proceedings-article","created":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T19:41:38Z","timestamp":1755546098000},"page":"2600-2605","source":"Crossref","is-referenced-by-count":0,"title":["Structured Instruction Parsing and Scene Alignment For UAV Vision-Language Navigation"],"prefix":"10.1109","author":[{"given":"Liangyu","family":"Zhou","sequence":"first","affiliation":[{"name":"Beihang University,School of Electronic and Information Engineering,Beijing,China,100191"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Xue","sequence":"additional","affiliation":[{"name":"Beihang University,School of Electronic and Information Engineering,Beijing,China,100191"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyan","family":"Luo","sequence":"additional","affiliation":[{"name":"Beihang University,School of Astronautics,Beijing,China,100191"}],"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\/ICCV51070.2023.01411"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref4","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01282"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6849"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1287"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1181"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_34"},{"key":"ref14","article-title":"Speaker-follower models for vision-and-language navigation","volume":"31","author":"Fried","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00689"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01488"},{"article-title":"Self-monitoring navigation agent via auxiliary progress estimation","year":"2019","author":"Ma","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01564"},{"article-title":"Vision and language navigation in the real world via online visual language mapping","year":"2023","author":"Xu","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01542"},{"article-title":"Clip-nav: Using clip for zero-shot vision-and-language navigation","year":"2022","author":"Dorbala","key":"ref22"},{"key":"ref23","first-page":"492","article-title":"Lmnav: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"Conference on robot learning","author":"Shah"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611565"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02554"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1287"}],"event":{"name":"2025 IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2025,9,14]]},"location":"Anchorage, AK, USA","end":{"date-parts":[[2025,9,17]]}},"container-title":["2025 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11084272\/11083968\/11084696.pdf?arnumber=11084696","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T05:00:44Z","timestamp":1755579644000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11084696\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,14]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icip55913.2025.11084696","relation":{},"subject":[],"published":{"date-parts":[[2025,9,14]]}}}