{"url":"/dataset/vidore","name":"Vidore","full_name":"Visual Document Retrieval Benchmark","description_markdown":"It is collection regrouping all datasets constituting the ViDoRe benchmark. It includes the test sets from different academic datasets (ArXiVQA, DocVQA, InfoVQA, TATDQA, TabFQuAD) and from datasets synthetically generated spanning various themes and industrial applications: (Artificial Intelligence, Government Reports, Healthcare Industry, Energy and Shift Project). Further details can be found on the corresponding dataset cards.","description_withheld":null,"homepage":"https://huggingface.co/spaces/vidore/vidore-leaderboard","introduced_date":"2024-06-27","introduced_date_note":null,"introduced_by":{"paper":"/paper/colpali-efficient-document-retrieval-with","title":"ColPali: Efficient Document Retrieval with Vision Language Models","first_author":"Manuel Faysse","url":null},"license":null,"modalities":[],"tasks":[{"name":"Text Retrieval","url":"/task/text-retrieval","datasets_with_task":"/datasets/task/text-retrieval"}],"languages":[],"variants":["Vidore"],"data_loaders":[],"num_papers_in_archive":13,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"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."}