{"url":"/dataset/mp-docvqa","name":"MP-DocVQA","full_name":"Multipage Document Visual Question Answering","description_markdown":"The dataset is aimed to perform Visual Question Answering on multipage industry scanned documents. The questions and answers are reused from Single Page DocVQA (SP-DocVQA) dataset. The images also corresponds to the same in original dataset with previous and posterior pages with a limit of up to 20 pages per document.","description_withheld":null,"homepage":"https://rrc.cvc.uab.es/?ch=17&com=introduction","introduced_date":"2023-02-19","introduced_date_note":null,"introduced_by":{"paper":"/paper/hierarchical-multimodal-transformers-for","title":"Hierarchical multimodal transformers for Multi-Page DocVQA","first_author":"Rubèn Tito","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"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":["MP-DocVQA"],"data_loaders":[],"num_papers_in_archive":10,"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."}