{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T18:43:57Z","timestamp":1766083437043,"version":"3.48.0"},"reference-count":72,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62301484"],"award-info":[{"award-number":["62301484"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007834","name":"Natural Science Foundation of Ningbo Municipality","doi-asserted-by":"publisher","award":["2024J454"],"award-info":[{"award-number":["2024J454"]}],"id":[{"id":"10.13039\/100007834","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jinhua Science and Technology Bureau Project","award":["2023-1-118"],"award-info":[{"award-number":["2023-1-118"]}]},{"DOI":"10.13039\/501100001809","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFB3209800"],"award-info":[{"award-number":["2023YFB3209800"]}],"id":[{"id":"10.13039\/501100001809","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.2025.3638946","type":"journal-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:43:01Z","timestamp":1764355381000},"page":"1-16","source":"Crossref","is-referenced-by-count":0,"title":["GeoFormer: Boosting Object Distinguishing and Prompt Understanding for Cross-View Object Geo-Localization"],"prefix":"10.1109","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1420-1909","authenticated-orcid":false,"given":"Xiaohan","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5143-4501","authenticated-orcid":false,"given":"Si-Yuan","family":"Cao","sequence":"additional","affiliation":[{"name":"Ningbo Innovation Center, Zhejiang University, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0636-7743","authenticated-orcid":false,"given":"Zhu","family":"Yu","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8846-980X","authenticated-orcid":false,"given":"Zhe","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7247-3670","authenticated-orcid":false,"given":"Xue","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8382-2976","authenticated-orcid":false,"given":"Xiaokai","family":"Bai","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1557-7166","authenticated-orcid":false,"given":"Beinan","family":"Yu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8469-019X","authenticated-orcid":false,"given":"Hui-Liang","family":"Shen","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Jinhua Institute, Zhejiang University, Jinhua, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref2","article-title":"EdgeSAM: Prompt-in-the-loop distillation for SAM","author":"Zhou","year":"2023","journal-title":"arXiv:2312.06660"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3307508"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS46834.2022.9883642"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2008.2002695"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2012.2233469"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241230562"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2024.105605"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00758"},{"key":"ref10","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":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00123"},{"key":"ref12","first-page":"29009","article-title":"Cross-view geo-localization with layer-to-layer transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yang"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3175601"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3210195"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3121337"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00848"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6875"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01545"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3443652"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02072"},{"key":"ref21","first-page":"5301","article-title":"Fine-grained cross-view geo-localization using a correlation-aware homography estimator","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Wang"},{"journal-title":"arXiv:1804.02767","article-title":"YOLOv3: An incremental improvement","author":"Redmon","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888758"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2025.3603506"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01652"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02097"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413896"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3152046"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01650"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3189702"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3336844"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12077"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/s24123719"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3689095.3689103"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00412"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00094"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00642"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00577"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00056"},{"key":"ref40","article-title":"Segment and track anything","author":"Cheng","year":"2023","journal-title":"arXiv:2305.06558"},{"key":"ref41","article-title":"Segment anything meets point tracking","author":"Raji\u010d","year":"2023","journal-title":"arXiv:2307.01197"},{"key":"ref42","article-title":"Interactive segment anything NeRF with feature imitation","author":"Chen","year":"2023","journal-title":"arXiv:2305.16233"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3416470"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01540"},{"key":"ref46","article-title":"CATs: Cost aggregation transformers for visual correspondence","author":"Cho","year":"2021","journal-title":"arXiv:2106.02520"},{"article-title":"An image is worth 16$\\times$\n16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy","key":"ref47"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"ref49","first-page":"18","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref50","first-page":"529","article-title":"LabelEnc: A new intermediate supervision method for object detection","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","author":"Miao"},{"key":"ref51","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3443455"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3346924"},{"key":"ref55","article-title":"YOLOE: Real-time seeing anything","author":"Wang","year":"2025","journal-title":"arXiv:2503.07465"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.23977\/acss.2023.070812"},{"key":"ref58","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke"},{"article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Loshchilov","key":"ref59"},{"volume-title":"YOLOv5 By Ultralytics","year":"2020","author":"Jocher","key":"ref60"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3363614"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00456"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3285228"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00564"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28554"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3273"},{"key":"ref70","first-page":"30392","article-title":"Early convolutions help transformers see better","volume-title":"Proc. NIPS","author":"Xiao"},{"article-title":"Student as an inherent denoiser of noisy teacher","volume-title":"Proc. 3rd Workshop Efficient Natural Lang. Speech Process. (ENLSP) NeurIPS","author":"Zhao","key":"ref71"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3335410"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10807682\/11271499.pdf?arnumber=11271499","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T18:33:32Z","timestamp":1766082812000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11271499\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2025.3638946","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"type":"print","value":"0196-2892"},{"type":"electronic","value":"1558-0644"}],"subject":[],"published":{"date-parts":[[2025]]}}}