{"url":"/dataset/doccvqa","name":"DocCVQA","full_name":"Document Collection Visual Question Answering","description_markdown":"DocCVQA is a Document Visual Question Answering dataset, where the questions are posed over a whole collection of 14,362 scanned documents. Therefore, the task can be seen as a retrieval-style evidence seeking task where given a question, the aim is to identify and retrieve all the documents in a large document collection that are relevant to answering this question as well as provide the answer.","description_withheld":null,"homepage":"https://rrc.cvc.uab.es/?ch=17&com=introduction","introduced_date":"2021-04-27","introduced_date_note":null,"introduced_by":{"paper":"/paper/document-collection-visual-question-answering","title":"Document Collection Visual Question Answering","first_author":"Rubèn Tito","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Visual Question Answering (VQA)","url":"/task/visual-question-answering","datasets_with_task":"/datasets/task/visual-question-answering"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["DocCVQA"],"data_loaders":[],"num_papers_in_archive":6,"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."}