{"url":"/dataset/coco-qa","name":"COCO-QA","full_name":null,"description_markdown":"**COCO-QA** is a dataset for visual question answering. It consists of:\r\n\r\n- 123287 images\r\n- 78736 train questions\r\n- 38948 test questions\r\n- 4 types of questions: object, number, color, location\r\n- Answers are all one-word.\r\n\r\nSource: [Exploring Models and Data for Image Question Answering](https://arxiv.org/pdf/1505.02074v4.pdf)","description_withheld":null,"homepage":"http://www.cs.toronto.edu/~mren/research/imageqa/data/cocoqa/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/exploring-models-and-data-for-image-question","title":"Exploring Models and Data for Image Question Answering","first_author":"Mengye Ren","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Visual Question Answering (VQA)","url":"/task/visual-question-answering","datasets_with_task":"/datasets/task/visual-question-answering"}],"languages":[],"variants":["COCO-QA"],"data_loaders":[],"num_papers_in_archive":62,"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."}