{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T06:24:13Z","timestamp":1765347853470,"version":"3.46.0"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Key Laboratory of Spatial-Temporal Big Data Analysis and Application of Natural Resources in Megacities, MNR,","award":["KFKT-2024-03"],"award-info":[{"award-number":["KFKT-2024-03"]}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","award":["22ZR1465700"],"award-info":[{"award-number":["22ZR1465700"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tgrs.2025.3635418","type":"journal-article","created":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T18:42:34Z","timestamp":1763664154000},"page":"1-19","source":"Crossref","is-referenced-by-count":0,"title":["AdaptGeo: Parameter-Efficient Cross-View Geo-Localization via Frozen Foundation Model and Transformer Adapter"],"prefix":"10.1109","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2906-2913","authenticated-orcid":false,"given":"Changjiang","family":"Yin","sequence":"first","affiliation":[{"name":"College of Surveying and Geo-Informatics, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4459-431X","authenticated-orcid":false,"given":"Junqi","family":"Luo","sequence":"additional","affiliation":[{"name":"College of Surveying and Geo-Informatics, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1056-9159","authenticated-orcid":false,"given":"Qin","family":"Ye","sequence":"additional","affiliation":[{"name":"College of Surveying and Geo-Informatics, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7280-4669","authenticated-orcid":false,"given":"Xiaohan","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Tongji University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00577"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3236662"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2018.04.006"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2909530"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/rs15205039"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3278257"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2024.05.006"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3121987"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.451"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3061265"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3491757"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3352418"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3396330"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00123"},{"key":"ref15","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref16","article-title":"Learning generalized zero-shot learners for open-domain image geolocalization","author":"Haas","year":"2023","journal-title":"arXiv:2302.00275"},{"key":"ref17","first-page":"8690","article-title":"GeoCLIP: Clip-inspired alignment between locations and images for effective worldwide geo-localization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cepeda"},{"key":"ref18","article-title":"Image segmentation in foundation model era: A survey","author":"Zhou","year":"2024","journal-title":"arXiv:2408.12957"},{"key":"ref19","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref20","article-title":"Towards a unified view of parameter-efficient transfer learning","author":"He","year":"2021","journal-title":"arXiv:2110.04366"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3425608"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3121337"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3210195"},{"key":"ref24","first-page":"10090","article-title":"Spatial-aware feature aggregation for image based cross-view geo-localization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Shi"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3144066"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6875"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00364"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00412"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3484330"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-024-05777-4"},{"key":"ref31","article-title":"Scale-adaptive UAV geo-localization via height-aware partition learning","author":"Chen","year":"2024","journal-title":"arXiv:2412.11535"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3424196"},{"key":"ref33","article-title":"Object-level cross-view geo-localization with location enhancement and multi-head cross attention","author":"Huang","year":"2025","journal-title":"arXiv:2505.17911"},{"key":"ref34","article-title":"A unified hierarchical framework for fine-grained cross-view geo-localization over large-scale scenarios","author":"Song","year":"2025","journal-title":"arXiv:2505.07622"},{"key":"ref35","article-title":"Robust drone-view geo-localization via content-viewpoint disentanglement","author":"Li","year":"2025","journal-title":"arXiv:2505.11822"},{"key":"ref36","article-title":"Where am I? Cross-view geo-localization with natural language descriptions","author":"Ye","year":"2024","journal-title":"arXiv:2412.17007"},{"key":"ref37","article-title":"GeoVLM: Improving automated vehicle geolocalisation using vision-language matching","author":"Dagda","year":"2025","journal-title":"arXiv:2505.13669"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3135013"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01545"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3296074"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref42","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref44","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2021","journal-title":"arXiv:2106.08254"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.5194\/isprs-archives-XLVIII-1-2024-821-2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00483"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01435"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.7"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.626"},{"key":"ref50","first-page":"1022","article-title":"Compacter: Efficient low-rank hypercomplex adapter layers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Mahabadi"},{"key":"ref51","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref52","article-title":"Vision transformer adapter for dense predictions","author":"Chen","year":"2022","journal-title":"arXiv:2205.08534"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00361"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref55","first-page":"16664","article-title":"AdaptFormer: Adapting vision transformers for scalable visual recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01199"},{"key":"ref58","article-title":"Parameter-efficient fine-tuning for pre-trained vision models: A survey and benchmark","author":"Xin","year":"2024","journal-title":"arXiv:2402.02242"},{"key":"ref59","article-title":"Parameter-efficient fine-tuning for large models: A comprehensive survey","author":"Han","year":"2024","journal-title":"arXiv:2403.14608"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.39"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_41"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32245"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27852"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3413174"},{"key":"ref67","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413896"},{"key":"ref69","first-page":"12116","article-title":"Do vision transformers see like convolutional neural networks?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Raghu"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249204"},{"key":"ref72","article-title":"Multimodal autoregressive pre-training of large vision encoders","author":"Fini","year":"2024","journal-title":"arXiv:2411.14402"},{"key":"ref73","article-title":"SigLIP 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features","author":"Tschannen","year":"2025","journal-title":"arXiv:2502.14786"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10807682\/11262226.pdf?arnumber=11262226","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T06:21:01Z","timestamp":1765347661000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11262226\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2025.3635418","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"type":"print","value":"0196-2892"},{"type":"electronic","value":"1558-0644"}],"subject":[],"published":{"date-parts":[[2025]]}}}