{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T06:07:18Z","timestamp":1781503638473,"version":"3.54.1"},"reference-count":55,"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\/iccv51701.2025.02334","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"25165-25175","source":"Crossref","is-referenced-by-count":2,"title":["MMGeo: Multimodal Compositional Geo-Localization for UAVs"],"prefix":"10.1109","author":[{"given":"Yuxiang","family":"Ji","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence, Xiamen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boyong","family":"He","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Xiamen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuoyue","family":"Tan","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Xiamen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liaoni","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Xiamen University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00118"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3060397"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01833"},{"key":"ref5","article-title":"Scale-adaptive uav geolocalization via height-aware partition learning","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3424196"},{"key":"ref7","article-title":"Composed image retrieval with text feedback via multi-grained uncertainty regularization","author":"Chen","year":"2024","journal-title":"ICLR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73247-8_13"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3346279"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01545"},{"key":"ref11","article-title":"An image is worth 16 16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105171"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611563"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793558"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3441491"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2019.8813809"},{"key":"ref18","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01672"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32409"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3343602"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197298"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3210880"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02516"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28081"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3290526"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-025-00086-x"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.120"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00565"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01587"},{"key":"ref32","article-title":"Towards seamless adaptation of pre-trained models for visual place recognition","volume-title":"The Twelfth International Conference on Learning Representations","author":"Lu"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2025.3585385"},{"key":"ref34","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11247374"},{"key":"ref36","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on machine learning","author":"Radford"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01850"},{"key":"ref38","author":"Schleiss","year":"2022","journal-title":"VPAIR - Aerial Visual Place Recognition and Localization in Large-scale Outdoor Environments"},{"key":"ref39","first-page":"948","article-title":"Lip-loc: Lidar image pretraining for cross-modal localization","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","author":"Shubodh"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00642"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611102"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00156"},{"key":"ref44","author":"Xu","year":"2024","journal-title":"UAV- VisLoc: A Large-scale Dataset for UAV Visual Localization"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01684"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3390\/app14167091"},{"key":"ref47","author":"Ye","year":"2024","journal-title":"Where am I? Cross-View Geo-localization with Natural Language Descriptions"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00158"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3238201"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3583006"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413896"},{"key":"ref52","author":"Zhou","year":"2023","journal-title":"Uni3D: Exploring Unified 3D Representation at Scale"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3346753"},{"key":"ref54","author":"Zhu","year":"2024","journal-title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00123"}],"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\/11446186.pdf?arnumber=11446186","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:24:26Z","timestamp":1777613066000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446186\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02334","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}