{"url":"/sota/photo-geolocation-estimation-on-gws15k","task":{"name":"Photo geolocation estimation","url":"/task/photo-geolocation-estimation","note":null},"dataset":{"name":"GWS15k","url":null},"category":"Computer Vision","categories":["Adversarial","Computer Vision","Graphs"],"category_note":null,"description":"**Photo geolocation estimation** is task of estimate or classify the geolocation from photos on world map.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Street level (1 km)","City level (25 km)","Region level (200 km)","Country level (750 km)","Continent level (2500 km)","Median Error (km)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Street level (1 km)":null,"City level (25 km)":null,"Region level (200 km)":null,"Country level (750 km)":null,"Continent level (2500 km)":null,"Median Error (km)":"lower"}},"counts":{"rows":5,"rows_with_code":4,"rows_with_paper_page":5,"rows_dated":5,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"PIGEOTTO","metrics":{"City level (25 km)":"9.2","Continent level (2500 km)":"85.1","Country level (750 km)":"65.7","Median Error (km)":"415.4","Region level (200 km)":"31.2","Street level (1 km)":"0.7"},"uses_additional_data":false,"paper_date":"2023-07-11","paper":"/paper/pigeon-predicting-image-geolocations","paper_url":"https://arxiv.org/abs/2307.05845v6","paper_title":"PIGEON: Predicting Image Geolocations","code":"https://github.com/LukasHaas/PIGEON","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":2,"model":"GeoDecoder","metrics":{"City level (25 km)":"1.5","Continent level (2500 km)":"50.5","Country level (750 km)":"26.9","Region level (200 km)":"8.7","Street level (1 km)":"0.7"},"uses_additional_data":false,"paper_date":"2023-03-07","paper":"/paper/where-we-are-and-what-we-re-looking-at-query","paper_url":"https://arxiv.org/abs/2303.04249v1","paper_title":"Where We Are and What We're Looking At: Query Based Worldwide Image Geo-localization Using Hierarchies and Scenes","code":null,"n_code_links":0,"syntology":{"n_ran":17,"n_unverified":6,"n_samples":23,"n_pointer_only_licence":23}},{"rank_in_archive_order":3,"model":"GeoCLIP","metrics":{"City level (25 km)":"3.1","Continent level (2500 km)":"74.1","Country level (750 km)":"45.7","Region level (200 km)":"16.9","Street level (1 km)":"0.6"},"uses_additional_data":false,"paper_date":"2023-09-27","paper":"/paper/geoclip-clip-inspired-alignment-between","paper_url":"https://arxiv.org/abs/2309.16020v2","paper_title":"GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization","code":"https://github.com/VicenteVivan/geo-clip","n_code_links":3,"syntology":{"n_ran":5,"n_unverified":8,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"Translocator","metrics":{"City level (25 km)":"1.1","Continent level (2500 km)":"48.3","Country level (750 km)":"25.5","Region level (200 km)":"8.0","Street level (1 km)":"0.5"},"uses_additional_data":false,"paper_date":"2022-04-29","paper":"/paper/where-in-the-world-is-this-image-transformer","paper_url":"https://arxiv.org/abs/2204.13861v2","paper_title":"Where in the World is this Image? Transformer-based Geo-localization in the Wild","code":"https://github.com/shramanpramanick/transformer_based_geo-localization","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"ISNs (M, f*, S3)","metrics":{"City level (25 km)":"0.6","Continent level (2500 km)":"38.5","Country level (750 km)":"15.5","Region level (200 km)":"4.2","Street level (1 km)":"0.05"},"uses_additional_data":false,"paper_date":"2018-09-01","paper":"/paper/geolocation-estimation-of-photos-using-a","paper_url":"http://openaccess.thecvf.com/content_ECCV_2018/html/Eric_Muller-Budack_Geolocation_Estimation_of_ECCV_2018_paper.html","paper_title":"Geolocation Estimation of Photos using a Hierarchical Model and Scene Classification","code":"https://github.com/TIBHannover/GeoEstimation","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 7,081 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":7081,"papers_extracted_not_yet_verified":217,"boards_without_verdict":27,"papers_not_yet_extracted":2325},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":4,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":4,"distinct_papers_with_any_sample_ran":4,"samples_over_distinct_papers":{"n_ran":24,"n_unverified":15,"n_samples":39,"n_pointer_only_licence":25,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":24,"n_unverified":15,"n_samples":39,"n_pointer_only_licence":25,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}