{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T19:51:57Z","timestamp":1783972317085,"version":"3.55.0"},"reference-count":122,"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\/iccv51701.2025.02688","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"28946-28958","source":"Crossref","is-referenced-by-count":5,"title":["UAVScenes: A Multi-Modal Dataset for UAVs"],"prefix":"10.1109","author":[{"given":"Sijie","family":"Wang","sequence":"first","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siqi","family":"Li","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yawei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shangshu","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Northeastern University,Shenyang,China,110819"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shenghai","family":"Yuan","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"She","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quanjiang","family":"Guo","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"JinXuan","family":"Zheng","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ong Kang","family":"Howe","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leonrich","family":"Chandra","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shrivarshann","family":"Srijeyan","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aditya","family":"Sivadas","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Toshan","family":"Aggarwal","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heyuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongming","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chujie","family":"Chen","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junyu","family":"Jiang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lihua","family":"Xie","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wee Peng","family":"Tay","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Semantic drone dataset"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2478\/aei-2023-0003"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00301"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.09.127"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref6","article-title":"Joint 2d-3d-semantic data for indoor scene understanding","author":"Armeni","year":"2017","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3649224"},{"key":"ref9","article-title":"Zoedepth: Zero-shot transfer by combining relative and metric depth","author":"Bhat","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00488"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915620033"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11246238"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2025.104429"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3142744"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCA51439.2020.9264577"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.106"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3264950"},{"key":"ref19","article-title":"Stpls3d: A large-scale synthetic and real aerial photogrammetry 3d point cloud dataset","author":"Chen","year":"2022","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Gaussianpro: 3d gaussian splatting with progressive propagation","author":"Cheng","year":"2024","journal-title":"ICML"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref22","article-title":"Alto: A large-scale dataset for uav visual place recognition and localization","author":"Cisneros","year":"2022","journal-title":"arXiv preprint"},{"key":"ref23","volume-title":"SpConv: Spatially sparse convolution library","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref25","article-title":"Compact 3d gaussian splatting for dense visual slam","author":"Deng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tase.2025.3617654"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2025.3536278"},{"key":"ref28","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref29","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proceedings of the 1st Annual Conference on Robot Learning","author":"Dosovitskiy","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_23"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCA.2013.6564974"},{"key":"ref32","article-title":"Hazydet: Open-source benchmark for drone-view object detection with depth-cues in hazy scenes","author":"Feng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00081"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611563"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00393"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.446"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3444912"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01672"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561251"},{"key":"ref43","article-title":"Go: The great outdoors multimodal dataset","author":"Jiang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"6g non-terrestrial networks enabled low-altitude economy: Opportunities and challenges","author":"Jiang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3343602"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.336"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophoto.2021.100001"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00183"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956458"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533373"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463644"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00077"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3210880"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241227968"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3390\/drones7030191"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11246032"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3179507"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811935"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_6"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11247236"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00799"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.05.009"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2022.3142663"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3299237"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.07.063"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.3390\/drones6060147"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00357"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3094157"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211052312"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00168"},{"key":"ref76","article-title":"Envodat: A large-scale multisensory dataset for robotic spatial awareness and semantic reasoning in heterogeneous environments","author":"Nwankwo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref77","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0276"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2846566"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3090981"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00235"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2909530"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3168279"},{"key":"ref87","first-page":"027836492","article-title":"Gosine. Mun-frl: A visual-inertial-lidar dataset for aerial autonomous navigation and mapping","author":"Ravindu","year":"2024","journal-title":"The International Journal of Robotics Research"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_30"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241278369"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i06.6608"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2020.105523"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02037"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON.2017.8227967"},{"key":"ref94","article-title":"Dc-gaussian: Improving 3d gaussian splatting for reflective dash cam videos","author":"Wang","year":"2024","journal-title":"NeurIPS"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i5.25765"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01868"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341801"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00156"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2415"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref102","article-title":"Gauu-scene: A scene reconstruction benchmark on large scale 3d reconstruction dataset using gaussian splatting","author":"Xiong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref103","article-title":"Gauu-scene v2: Assessing the reliability of image-based metrics with expansive lidar image dataset using 3dgs and nerf","author":"Xiong","year":"2024","journal-title":"CoRR"},{"key":"ref104","article-title":"Uav-visloc: A largescale dataset for uav visual localization","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/icca62789.2024.10591842"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161194"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01684"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref109","article-title":"Depth anything v2","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCV57592.2022.10004288"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610206"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00423"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCV.2014.7064275"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72655-2_19"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981107"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413896"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3346753"},{"key":"ref120","article-title":"Vision meets drones: A challenge","author":"Zhu","year":"2018","journal-title":"arXiv preprint"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249204"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3234802"}],"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\/11445872.pdf?arnumber=11445872","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T20:05:49Z","timestamp":1781813149000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445872\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":122,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02688","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}