{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:41:15Z","timestamp":1781797275056,"version":"3.54.5"},"reference-count":56,"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"}],"funder":[{"DOI":"10.13039\/501100001666","name":"The National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42201358"],"award-info":[{"award-number":["42201358"]}],"id":[{"id":"10.13039\/501100001666","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00557","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"5890-5900","source":"Crossref","is-referenced-by-count":3,"title":["Where am I? Cross-View Geo-localization with Natural Language Descriptions"],"prefix":"10.1109","author":[{"given":"Junyan","family":"Ye","sequence":"first","affiliation":[{"name":"Sun Yat-Sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Honglin","family":"Lin","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leyan","family":"Ou","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dairong","family":"Chen","sequence":"additional","affiliation":[{"name":"Wuhan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihao","family":"Wang","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Zhu","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Conghui","family":"He","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weijia","family":"Li","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"issue":"10","key":"ref1","first-page":"105","article-title":"Seitz, and Richard Szeliski","volume":"54","author":"Agarwal","year":"2011","journal-title":"Building rome in a day. Communications of the ACM"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref3","year":"2024","journal-title":"The claude 3 model family: Opus, sonnet, haiku"},{"key":"ref4","article-title":"Latteclip: Unsupervised clip fine-tuning via 1 mm-synthetic texts","author":"Cao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00045"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01282"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72913-3_12"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref9","first-page":"3","article-title":"Towards natural language-guided drones: Geotext-1652 benchmark with spatially relation matching","author":"Chu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01545"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105171"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_27"},{"key":"ref14","first-page":"2","author":"He","year":"2023","journal-title":"From crowdsourcing to large multimodal models: Toward enhancing image data annotation with gpt-4v."},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02489"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206587"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3343602"},{"key":"ref19","first-page":"5583","article-title":"Vilt: Vision-andlanguage transformer without convolution or region supervision","volume-title":"In International conference on machine learning","author":"Kim"},{"key":"ref20","article-title":"Adam: A method for stochastic optimization","volume-title":"arXiv preprint","author":"Kingma","year":"2014"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00657"},{"key":"ref22","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified visionlanguage understanding and generation","volume-title":"In International conference on machine learning","author":"Li"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01669"},{"key":"ref24","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"In Text summarization branches out"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00577"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920931151"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-56414-2_5"},{"key":"ref28","first-page":"2","volume":"3","year":"2024","journal-title":"OpenAI. Hello gpt-4o."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3227513"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In International conference on machine learning","author":"Radford"},{"key":"ref31","first-page":"2","article-title":"A survey of hallucination in large foundation models","author":"Rawte","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01300"},{"key":"ref33","first-page":"6","article-title":"Spatialaware feature aggregation for image based cross-view geolocalization","volume":"32","author":"Shi","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00412"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681518"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref37","article-title":"Fine-grained cross-view geo-localization using a correlation-aware homography estimator","volume":"36","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2015.451"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.01.027"},{"key":"ref40","first-page":"14958","article-title":"Henriques, and Daniel Cremers","volume-title":"Text2loc: 3D point cloud localization from natural language. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Xia"},{"key":"ref41","first-page":"397","article-title":"Kooij","volume-title":"Adapting fine-grained cross-view localization to areas without fine ground truth. In European Conference on Computer Vision","author":"Xia"},{"key":"ref42","article-title":"Gpt-imgeval: A comprehensive benchmark for diagnosing gpt4o in image generation","author":"Yan","year":"2025","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611709"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02621"},{"key":"ref45","first-page":"1","article-title":"Cross-view image geolocalization with panorama-bev co-retrieval network","author":"Ye","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Loki: A comprehensive synthetic data detection benchmark using large multimodal models","author":"Ye","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2025.3585358"},{"key":"ref48","first-page":"25994","article-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","volume-title":"In International Conference on Machine Learning","author":"Zeng"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72983-6_18"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25457"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72933-1_10"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413896"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33163"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00364"}],"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\/11443395.pdf?arnumber=11443395","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:06:29Z","timestamp":1777611989000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443395\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00557","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}