{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:31:59Z","timestamp":1777865519781,"version":"3.51.4"},"reference-count":59,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00559","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"5912-5922","source":"Crossref","is-referenced-by-count":0,"title":["CityNav: A Large-Scale Dataset for Real-World Aerial Navigation"],"prefix":"10.1109","author":[{"given":"Jungdae","family":"Lee","sequence":"first","affiliation":[{"name":"Institute of Science Tokyo"}]},{"given":"Taiki","family":"Miyanishi","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]},{"given":"Shuhei","family":"Kurita","sequence":"additional","affiliation":[{"name":"National Institute of Informatics"}]},{"given":"Koya","family":"Sakamoto","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]},{"given":"Daichi","family":"Azuma","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]},{"given":"Yutaka","family":"Matsuo","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]},{"given":"Nakamasa","family":"Inoue","sequence":"additional","affiliation":[{"name":"Institute of Science Tokyo"}]}],"member":"263","reference":[{"key":"ref1","author":"Anderson","year":"2018","journal-title":"On evaluation of embodied navigation agents"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref3","first-page":"671","article-title":"Sim-to-real transfer for vision-and-language navigation","volume-title":"Proceedings of the Conference on Robot Learning (CoRL)","author":"Anderson"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.170"},{"key":"ref5","article-title":"ARKitscenes - a diverse real-world dataset for 3d indoor scene understanding using mobile RGB-d data","volume-title":"Proceedings of Neural Information Processing Systems Datasets and Benchmarks Track (NeurIPS D&B)","author":"Baruch"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref7","first-page":"671","article-title":"Object goal navigation using goal-oriented semantic exploration","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS)","author":"Singh Chaplot"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01282"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610178"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00008"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.190"},{"key":"ref14","author":"Gao","year":"2024","journal-title":"Embodiedcity: A benchmark platform for embodied agent in real-world city environment"},{"key":"ref15","first-page":"3","author":"Gao","year":"2025","journal-title":"Openfly: A comprehensive platform for aerial vision-language navigation"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00430"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6849"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01554-9"},{"key":"ref19","first-page":"2","article-title":"An embodied generalist agent in 3d world","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Huang"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1181"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01549"},{"key":"ref22","first-page":"2","author":"Kolve","year":"2017","journal-title":"AI2-THOR: An Interactive 3D Environment for Visual AI"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01433"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref26","first-page":"3","author":"Lam","year":"2018","journal-title":"xview: Objects in context in overhead imagery"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00597"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01411"},{"key":"ref30","first-page":"1","article-title":"Instructnav: Zero-shot system for generic instruction navigation in unexplored environment","author":"Long","year":"2024","journal-title":"CoRL"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611565"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01560"},{"key":"ref33","first-page":"1","article-title":"Learning to navigate in cities without a map","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS)","author":"Mirowski"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1287"},{"key":"ref35","first-page":"77758","article-title":"Cityrefer: Geography-aware 3d visual grounding dataset on city-scale point cloud data","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS)","author":"Miyanishi"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1063"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref38","first-page":"2","article-title":"Habitat-matterport 3d dataset (HM3d): 1000 largescale 3d environments for embodied AI","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS)","author":"Kumar Ramakrishnan"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00511"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref41","first-page":"4","article-title":"Potree: Rendering large point clouds in web browsers","author":"Sch\u00fctz","year":"2016","journal-title":"Technische Universit\u00e4t Wien, Wiede\u0144"},{"key":"ref42","first-page":"492","article-title":"Lm-nav: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"Proceedings of the Conference on Robot Learning (CoRL)","author":"Shah"},{"key":"ref43","first-page":"2","article-title":"Knowledge-based embodied question answering","volume":"abs\/2109.07872","author":"Tan","year":"2021","journal-title":"ArXiv"},{"key":"ref44","first-page":"394406","article-title":"Vision-and-dialog navigation","volume-title":"Proceedings of the Conference on Robot Learning (CoRL)","author":"Thomason"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01374-3"},{"key":"ref46","first-page":"2","author":"Wang","year":"2024","journal-title":"Grutopia: Dream general robots in a city at scale"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01868"},{"key":"ref48","first-page":"3","article-title":"Towards realistic uav vision-language navigation: Platform, benchmark, and methodology","volume-title":"International Conference on Learning Representations (ICLR)","author":"Wang"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00682"},{"key":"ref50","first-page":"1","article-title":"Metaurban: An embodied ai simulation platform for urban micromobility","volume-title":"International Conference on Learning Representations (ICLR)","author":"Wu"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00945"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_3"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00647"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.079"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.630"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_15"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01250"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444204.pdf?arnumber=11444204","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:45:43Z","timestamp":1777531543000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444204\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00559","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}