{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T17:58:40Z","timestamp":1787162320749,"version":"build-2736575974"},"reference-count":78,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42201477"],"award-info":[{"award-number":["42201477"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42130105"],"award-info":[{"award-number":["42130105"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Fusion"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.inffus.2026.104562","type":"journal-article","created":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T00:06:59Z","timestamp":1781827619000},"page":"104562","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["OSMLoc: Single image-based visual localization in OpenStreetMap with fused geometric and semantic guidance"],"prefix":"10.1016","volume":"136","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9926-4832","authenticated-orcid":false,"given":"Youqi","family":"Liao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0955-6681","authenticated-orcid":false,"given":"Xieyuanli","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3290-7274","authenticated-orcid":false,"given":"Shuhao","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4813-5126","authenticated-orcid":false,"given":"Jianping","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0152-3300","authenticated-orcid":false,"given":"Zhen","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0051-7451","authenticated-orcid":false,"given":"Hongchao","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7736-0803","authenticated-orcid":false,"given":"Bisheng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.inffus.2026.104562_bib0001","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.inffus.2017.01.001","article-title":"Cooperative localization for disconnected sensor networks and a mobile robot in friendly environments","volume":"37","author":"Yuan","year":"2017","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104562_bib0002","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3640","article-title":"Vigor: cross-view image geo-localization beyond one-to-one retrieval","author":"Zhu","year":"2021"},{"key":"10.1016\/j.inffus.2026.104562_bib0003","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.inffus.2023.03.006","article-title":"UPLP-SLAM: unified point-line-plane feature fusion for RGB-D visual SLAM","volume":"96","author":"Yang","year":"2023","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104562_bib0004","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103009","article-title":"Learning and grounding visual multimodal adaptive graph for visual navigation","volume":"118","author":"Zhou","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104562_bib0005","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"5297","article-title":"NetVLAD: CNN architecture for weakly supervised place recognition","author":"Arandjelovic","year":"2016"},{"key":"10.1016\/j.inffus.2026.104562_bib0006","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.inffus.2017.01.003","article-title":"Information fusion in content based image retrieval: a comprehensive overview","volume":"37","author":"Piras","year":"2017","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104562_bib0007","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14141","article-title":"Patch-NetVLAD: multi-scale fusion of locally-global descriptors for place recognition","author":"Hausler","year":"2021"},{"key":"10.1016\/j.inffus.2026.104562_bib0008","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.inffus.2020.10.008","article-title":"Image retrieval from remote sensing big data: a survey","volume":"67","author":"Li","year":"2021","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104562_bib0009","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1016\/j.isprsjprs.2020.12.013","article-title":"Deep regression for LiDAR-based localization in dense urban areas","volume":"172","author":"Yu","year":"2021","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.inffus.2026.104562_bib0010","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1016\/j.isprsjprs.2022.10.009","article-title":"I2D-Loc: camera localization via image to LiDAR depth flow","volume":"194","author":"Chen","year":"2022","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.inffus.2026.104562_bib0011","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1016\/j.isprsjprs.2021.12.011","article-title":"An improved lightweight deep neural network with knowledge distillation for local feature extraction and visual localization using images and LiDAR point clouds","volume":"184","author":"Shi","year":"2022","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.inffus.2026.104562_bib0012","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1016\/j.isprsjprs.2023.11.005","article-title":"PatchAugNet: patch feature augmentation-based heterogeneous point cloud place recognition in large-scale street scenes","volume":"206","author":"Zou","year":"2023","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.inffus.2026.104562_bib0013","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/j.isprsjprs.2024.07.019","article-title":"A framework for fully automated reconstruction of semantic building model at urban-scale using textured LoD2 data","volume":"216","author":"Wang","year":"2024","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.inffus.2026.104562_bib0014","unstructured":"OSM_Foundation, OSM static, 2024, https:\/\/planet.openstreetmap.org\/statistics\/data_stats.html."},{"issue":"4","key":"10.1016\/j.inffus.2026.104562_bib0015","doi-asserted-by":"crossref","first-page":"700","DOI":"10.1080\/13658816.2013.867495","article-title":"Quality assessment for building footprints data on OpenStreetMap","volume":"28","author":"Fan","year":"2014","journal-title":"Int. J. Geogr. Inf. Sci."},{"issue":"1","key":"10.1016\/j.inffus.2026.104562_bib0016","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1109\/MGRS.2020.2994107","article-title":"OpenStreetMap: challenges and opportunities in machine learning and remote sensing","volume":"9","author":"Vargas-Munoz","year":"2020","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"10.1016\/j.inffus.2026.104562_bib0017","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXIII 16","first-page":"502","article-title":"You are here: geolocation by embedding maps and images","author":"Samano","year":"2020"},{"key":"10.1016\/j.inffus.2026.104562_bib0018","series-title":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"5507","article-title":"Efficient localisation using images and OpenStreetMaps","author":"Zhou","year":"2021"},{"key":"10.1016\/j.inffus.2026.104562_bib0019","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"21632","article-title":"OrienterNet: visual localization in 2D public maps with neural matching","author":"Sarlin","year":"2023"},{"key":"10.1016\/j.inffus.2026.104562_bib0020","series-title":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"13198","article-title":"MaploCNet: coarse-to-fine feature registration for visual re-localization in navigation maps","author":"Wu","year":"2024"},{"key":"10.1016\/j.inffus.2026.104562_bib0021","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11621","article-title":"nuscenes: a multimodal dataset for autonomous driving","author":"Caesar","year":"2020"},{"key":"10.1016\/j.inffus.2026.104562_bib0022","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8748","article-title":"ArgoVerse: 3D tracking and forecasting with rich maps","author":"Chang","year":"2019"},{"key":"10.1016\/j.inffus.2026.104562_bib0023","first-page":"2835","article-title":"DINOv2: learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.inffus.2026.104562_bib0024","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10371","article-title":"Depth anything: unleashing the power of large-scale unlabeled data","author":"Yang","year":"2024"},{"key":"10.1016\/j.inffus.2026.104562_bib0025","series-title":"2011 International Conference on Computer Vision","first-page":"667","article-title":"Fast image-based localization using direct 2D-to-3D matching","author":"Sattler","year":"2011"},{"issue":"1","key":"10.1016\/j.inffus.2026.104562_bib0026","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1109\/TIP.2016.2623488","article-title":"A data-driven point cloud simplification framework for city-scale image-based localization","volume":"26","author":"Cheng","year":"2016","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.inffus.2026.104562_bib0027","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.isprsjprs.2020.01.008","article-title":"3D map-guided single indoor image localization refinement","volume":"161","author":"Li","year":"2020","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.inffus.2026.104562_bib0028","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"891","article-title":"Cross-view image geolocalization","author":"Lin","year":"2013"},{"key":"10.1016\/j.inffus.2026.104562_bib0029","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3608","article-title":"Cross-view image matching for geo-localization in urban environments","author":"Tian","year":"2017"},{"key":"10.1016\/j.inffus.2026.104562_bib0030","first-page":"7697","article-title":"SNAP: self-supervised neural maps for visual positioning and semantic understanding","volume":"36","author":"Sarlin","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104562_bib0031","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16719","article-title":"Unleashing unlabeled data: a paradigm for cross-view geo-localization","author":"Li","year":"2024"},{"key":"10.1016\/j.inffus.2026.104562_bib0032","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2626","article-title":"Mapillary street-level sequences: a dataset for lifelong place recognition","author":"Warburg","year":"2020"},{"key":"10.1016\/j.inffus.2026.104562_bib0033","unstructured":"Grab_Holdings, Kartaview, 2024, https:\/\/kartaview.org\/."},{"key":"10.1016\/j.inffus.2026.104562_bib0034","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1016\/j.inffus.2018.03.006","article-title":"Visual and textual information fusion using kernel method for content based image retrieval","volume":"44","author":"Unar","year":"2018","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104562_bib0035","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.inffus.2018.11.004","article-title":"Content based image retrieval using image features information fusion","volume":"51","author":"Ahmed","year":"2019","journal-title":"Inf. Fusion"},{"issue":"2","key":"10.1016\/j.inffus.2026.104562_bib0036","doi-asserted-by":"crossref","first-page":"974","DOI":"10.1109\/LRA.2023.3235682","article-title":"Hot-NetVLAD: learning discriminatory key points for visual place recognition","volume":"8","author":"Li","year":"2023","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.inffus.2026.104562_bib0037","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19370","article-title":"R2former: unified retrieval and reranking transformer for place recognition","author":"Zhu","year":"2023"},{"key":"10.1016\/j.inffus.2026.104562_bib0038","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8092","article-title":"D2-net: a trainable CNN for joint description and detection of local features","author":"Dusmanu","year":"2019"},{"key":"10.1016\/j.inffus.2026.104562_bib0039","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4938","article-title":"Superglue: learning feature matching with graph neural networks","author":"Sarlin","year":"2020"},{"key":"10.1016\/j.inffus.2026.104562_bib0040","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"2938","article-title":"PoseNet: a convolutional network for real-time 6-DoF camera relocalization","author":"Kendall","year":"2015"},{"key":"10.1016\/j.inffus.2026.104562_bib0041","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1016\/j.isprsjprs.2020.06.010","article-title":"PoseGAN: a pose-to-image translation framework for camera localization","volume":"166","author":"Liu","year":"2020","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.inffus.2026.104562_bib0042","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1016\/j.isprsjprs.2023.12.006","article-title":"TransCNNLoc: end-to-end pixel-level learning for 2D-to-3D pose estimation in dynamic indoor scenes","volume":"207","author":"Tang","year":"2024","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.inffus.2026.104562_bib0043","series-title":"2013 IEEE International Conference on Robotics and Automation","first-page":"1054","article-title":"OpenStreetSLAM: global vehicle localization using openstreetmaps","author":"Floros","year":"2013"},{"key":"10.1016\/j.inffus.2026.104562_bib0044","series-title":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"3305","article-title":"Augmenting vision with radar for all-weather geo-localization without a prior HD map","author":"Dong","year":"2024"},{"key":"10.1016\/j.inffus.2026.104562_bib0045","unstructured":"Z. Zhou, Z. Qi, L. Cheng, G. Xiong, SegLocNet: multimodal localization network for autonomous driving via bird\u2019s-eye-view segmentation, arXiv preprint arXiv: 2502.20077(2025)."},{"key":"10.1016\/j.inffus.2026.104562_bib0046","series-title":"2019 European Conference on Mobile Robots (ECMR)","first-page":"1","article-title":"Global localization on openstreetmap using 4-bit semantic descriptors","author":"Yan","year":"2019"},{"issue":"2","key":"10.1016\/j.inffus.2026.104562_bib0047","doi-asserted-by":"crossref","first-page":"4999","DOI":"10.1109\/LRA.2022.3152476","article-title":"Openstreetmap-based LiDAR global localization in urban environment without a prior LiDAR map","volume":"7","author":"Cho","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.inffus.2026.104562_bib0048","doi-asserted-by":"crossref","first-page":"2888","DOI":"10.1109\/TRO.2024.3392149","article-title":"Autonomous vehicle localization without prior high-definition map","volume":"40","author":"Lee","year":"2024","journal-title":"IEEE Trans. Robot."},{"key":"10.1016\/j.inffus.2026.104562_bib0049","unstructured":"S. Kang, M.Y. Liao, Y. Xia, O. Wysocki, B. Jutzi, D. Cremers, Opal: visibility-aware LiDAR-to-openstreetmap place recognition via adaptive radial fusion, arXiv preprint arXiv: 2504.19258(2025)."},{"key":"10.1016\/j.inffus.2026.104562_bib0050","series-title":"2023 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"2774","article-title":"Bevfusion: multi-task multi-sensor fusion with unified bird\u2019s-eye view representation","author":"Liu","year":"2023"},{"key":"10.1016\/j.inffus.2026.104562_bib0051","doi-asserted-by":"crossref","first-page":"362","DOI":"10.1016\/j.isprsjprs.2025.04.009","article-title":"VecMapLocNet: vision-based UAV localization using vector maps in GNSS-denied environments","volume":"225","author":"Wang","year":"2025","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.inffus.2026.104562_bib0052","series-title":"International Conference on Learning Representations","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"issue":"2","key":"10.1016\/j.inffus.2026.104562_bib0053","doi-asserted-by":"crossref","first-page":"1286","DOI":"10.1109\/LRA.2023.3343602","article-title":"Anyloc: towards universal visual place recognition","volume":"9","author":"Keetha","year":"2023","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.inffus.2026.104562_bib0054","series-title":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"1381","article-title":"FM-LOC: using foundation models for improved vision-based localization","author":"Mirjalili","year":"2023"},{"key":"10.1016\/j.inffus.2026.104562_bib0055","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XIV 16","first-page":"194","article-title":"Lift, splat, shoot: encoding images from arbitrary camera rigs by implicitly unprojecting to 3d","author":"Philion","year":"2020"},{"key":"10.1016\/j.inffus.2026.104562_bib0056","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"17225","article-title":"SliceMatch: geometry-guided aggregation for cross-view pose estimation","author":"Lentsch","year":"2023"},{"key":"10.1016\/j.inffus.2026.104562_bib0057","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9043","article-title":"Metric3D: towards zero-shot metric 3D prediction from a single image","author":"Yin","year":"2023"},{"key":"10.1016\/j.inffus.2026.104562_bib0058","series-title":"The Thirteenth International Conference on Learning Representations","article-title":"Depth pro: sharp monocular metric depth in less than a second","author":"Bochkovskiy","year":"2025"},{"issue":"1635","key":"10.1016\/j.inffus.2026.104562_bib0059","doi-asserted-by":"crossref","DOI":"10.1098\/rstb.2012.0533","article-title":"Neural systems for landmark-based wayfinding in humans","volume":"369","author":"Epstein","year":"2014","journal-title":"Philos. Trans. R. Soc. B Biol. Sci."},{"issue":"11","key":"10.1016\/j.inffus.2026.104562_bib0060","doi-asserted-by":"crossref","first-page":"1504","DOI":"10.1038\/nn.4656","article-title":"The cognitive map in humans: spatial navigation and beyond","volume":"20","author":"Epstein","year":"2017","journal-title":"Nat. Neurosci."},{"key":"10.1016\/j.inffus.2026.104562_bib0061","series-title":"Conference on Robot Learning (CoRL)","article-title":"Learning to localize using a LiDAR intensity map","author":"Barsan","year":"2018"},{"key":"10.1016\/j.inffus.2026.104562_bib0062","unstructured":"Mapillary, Mapillary website, 2024, https:\/\/www.mapillary.com\/."},{"key":"10.1016\/j.inffus.2026.104562_bib0063","unstructured":"OSM, OSM website, 2024, https:\/\/www.openstreetmap.org\/."},{"key":"10.1016\/j.inffus.2026.104562_bib0064","series-title":"2012 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3354","article-title":"Are we ready for autonomous driving? the KITTI vision benchmark suite","author":"Geiger","year":"2012"},{"key":"10.1016\/j.inffus.2026.104562_bib0065","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"17010","article-title":"Beyond cross-view image retrieval: highly accurate vehicle localization using satellite image","author":"Shi","year":"2022"},{"key":"10.1016\/j.inffus.2026.104562_bib0066","series-title":"European Conference on Computer Vision","first-page":"90","article-title":"Visual cross-view metric localization with dense uncertainty estimates","author":"Xia","year":"2022"},{"key":"10.1016\/j.inffus.2026.104562_bib0067","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.inffus.2026.104562_bib0068","unstructured":"K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition, arXiv preprint arXiv: 1409.1556(2014)."},{"key":"10.1016\/j.inffus.2026.104562_bib0069","unstructured":"O.A. van den, Y. Li, O. Vinyals, Representation learning with contrastive predictive coding, arXiv preprint arXiv: 1807.03748(2018)."},{"key":"10.1016\/j.inffus.2026.104562_bib0070","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"8448","article-title":"Towards unconstrained cross-view pose estimation","author":"Wollam","year":"2026"},{"key":"10.1016\/j.inffus.2026.104562_bib0071","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10012","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.inffus.2026.104562_bib0072","unstructured":"D.P. Kingma, J. Ba, Adam: a method for stochastic optimization, arXiv preprint arXiv: 1412.6980(2014)."},{"key":"10.1016\/j.inffus.2026.104562_bib0073","unstructured":"C. Zhang, D. Han, Y. Qiao, J.U. Kim, S.-H. Bae, S. Lee, C.S. Hong, Faster segment anything: towards lightweight SAM for mobile applications, arXiv preprint arXiv: 2306.14289(2023)."},{"key":"10.1016\/j.inffus.2026.104562_bib0074","unstructured":"G. Hinton, O. Vinyals, J. Dean, Distilling the knowledge in a neural network, arXiv preprint arXiv: 1503.02531(2015)."},{"key":"10.1016\/j.inffus.2026.104562_bib0075","series-title":"2021 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"5802","article-title":"Range image-based LiDAR localization for autonomous vehicles","author":"Chen","year":"2021"},{"issue":"3","key":"10.1016\/j.inffus.2026.104562_bib0076","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1145\/504729.504754","article-title":"Probabilistic robotics","volume":"45","author":"Thrun","year":"2002","journal-title":"Commun. ACM"},{"key":"10.1016\/j.inffus.2026.104562_bib0077","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"4418","article-title":"Argus: a compact and versatile foundation model for vision","author":"Zhuang","year":"2025"},{"key":"10.1016\/j.inffus.2026.104562_bib0078","unstructured":"O. Sim\u00e9oni, H.V. Vo, M. Seitzer, F. Baldassarre, M. Oquab, C. Jose, V. Khalidov, M. Szafraniec, S. Yi, M. Ramamonjisoa, et al., Dinov3, arXiv preprint arXiv: 2508.10104(2025)."}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526004409?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526004409?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:50:15Z","timestamp":1785891015000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1566253526004409"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":78,"alternative-id":["S1566253526004409"],"URL":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104562","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"OSMLoc: Single image-based visual localization in OpenStreetMap with fused geometric and semantic guidance","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104562","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104562"}}