{"url":"/dataset/soundingearth","name":"SoundingEarth","full_name":null,"description_markdown":"SoundingEarth consists of co-located aerial imagery and audio samples all around the world.","description_withheld":null,"homepage":"https://github.com/khdlr/SoundingEarth","introduced_date":"2021-08-02","introduced_date_note":null,"introduced_by":{"paper":"/paper/self-supervised-audiovisual-representation","title":"Self-supervised Audiovisual Representation Learning for Remote Sensing Data","first_author":"Konrad Heidler","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Cross-Modal Retrieval","url":"/task/cross-modal-retrieval","datasets_with_task":"/datasets/task/cross-modal-retrieval"}],"languages":[],"variants":["SoundingEarth"],"data_loaders":[],"num_papers_in_archive":8,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/cross-modal-retrieval-on-soundingearth","task":"Cross-Modal Retrieval","dataset_variant":"SoundingEarth","rows":2,"metrics":["Median Rank","Image-to-sound R@100","Sound-to-image R@100"],"first_row_in_archive_order":{"model":"GeoCLAP","paper":"/paper/learning-tri-modal-embeddings-for-zero-shot","metrics":{"Image-to-sound R@100":"0.434","Median Rank":"159","Sound-to-image R@100":"0.434"},"code_links":[{"title":"mvrl/geoclap","url":"https://github.com/mvrl/geoclap"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/learning-tri-modal-embeddings-for-zero-shot","title":"Learning Tri-modal Embeddings for Zero-Shot Soundscape Mapping","date":"2023-09-19","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":5,"samples_unverified":5,"pointer_only_for_licence":10,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/self-supervised-audiovisual-representation","title":"Self-supervised Audiovisual Representation Learning for Remote Sensing Data","date":"2021-08-02","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":10,"samples_ran":5,"samples_unverified":5,"pointer_only_for_licence":10,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}