{"url":"/dataset/earthvqa","name":"EarthVQA","full_name":"A multi-modal multi-task VQA dataset for remote sensing","description_markdown":"Earth vision research typically focuses on extracting geospatial object locations and categories but neglects the exploration of relations between objects and comprehensive reasoning. Based on city planning needs, we develop a multi-modal multi-task VQA dataset (EarthVQA) to advance relational reasoning-based judging, counting, and comprehensive analysis. The EarthVQA dataset contains 6000 images, corresponding semantic masks, and 208,593 QA pairs with urban and rural governance requirements embedded. \r\n\r\nCharacteristics:\r\n\r\n-  **Multi-level annotations**: The paired  image-mask-QA pairs assisst for relational reasoning-based remote sensing visual question answering.\r\n\r\n-  **Applicable QA pairs**: All QA pairs are designed based on the actual city planning needs.","description_withheld":null,"homepage":"","introduced_date":"2024-05-12","introduced_date_note":null,"introduced_by":{"paper":"/paper/earthvqa-towards-queryable-earth-via","title":"EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering","first_author":"Junjue Wang","url":null},"license":{"name":"CC BY-NC","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"Visual Question Answering","url":"/task/visual-question-answering-1","datasets_with_task":"/datasets/task/visual-question-answering-1"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["EarthVQA"],"data_loaders":[],"num_papers_in_archive":6,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/visual-question-answering-on-earthvqa","task":"Visual Question Answering","dataset_variant":"EarthVQA","rows":1,"metrics":["Overall Accuracy"],"first_row_in_archive_order":{"model":"SOBA","paper":"/paper/earthvqa-towards-queryable-earth-via","metrics":{"Overall Accuracy":"78.14"},"code_links":[{"title":"Junjue-Wang/EarthVQA","url":"https://github.com/Junjue-Wang/EarthVQA"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/earthvqa-towards-queryable-earth-via","title":"EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering","date":"2023-12-19","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":6,"samples_unverified":0,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":6,"samples_ran":6,"samples_unverified":0,"pointer_only_for_licence":6,"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."}