{"url":"/dataset/ocr-vqa","name":"OCR-VQA","full_name":null,"description_markdown":"The **OCR-VQA dataset** is a valuable resource for research in the field of **Visual Question Answering (VQA)**. Let me provide you with some details about it:\r\n\r\n1. **Dataset Overview**:\r\n    - The **OCR-VQA dataset** contains a total of **207,572 images** along with their associated **question-answer pairs**.\r\n    - These images are related to **document content** and are accompanied by their corresponding **OCR transcriptions**¹².\r\n\r\n2. **Purpose and Significance**:\r\n    - **Visual Question Answering (VQA)** tasks require models to reason jointly over visual information (such as images) and natural language inputs (such as questions).\r\n    - By using this dataset, researchers can develop and evaluate AI models that can effectively understand and answer questions based on visual content and textual context.\r\n\r\n3. **Other Related VQA Datasets**:\r\n    - Apart from OCR-VQA, there are other VQA datasets available for research and benchmarking:\r\n        - **ScreenQA**: Focused on questions related to screen content.\r\n        - **MP-DocVQA**: A dataset for document-based VQA.\r\n        - **ChartQA**: Specifically designed for answering questions about charts.\r\n        - **InfographicVQA**: For handling questions related to infographics.\r\n\r\nSource: Conversation with Bing, 3/15/2024\r\n(1) OCR-VQA Dataset | Papers With Code. https://paperswithcode.com/dataset/ocr-vqa.\r\n(2) GitHub - anisha2102/docvqa: Document Visual Question Answering. https://github.com/anisha2102/docvqa.\r\n(3) VQA: Visual Question Answering. https://visualqa.org/.\r\n(4) allenai/aokvqa: Official repository for the A-OKVQA dataset - GitHub. https://github.com/allenai/aokvqa.","description_withheld":null,"homepage":"https://ocr-vqa.github.io/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["OCR-VQA"],"data_loaders":[],"num_papers_in_archive":2,"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."}