{"url":"/dataset/chiqa","name":"ChiQA","full_name":"Chinese VQA","description_markdown":"ChiQA is a dataset designed for visual question answering tasks that not only measures the relatedness but also measures the answerability, which demands more fine-grained vision and language reasoning. It contains more than 40K questions and more than 200K question-images pairs. The questions are real-world image-independent queries that are more various and unbiased.","description_withheld":null,"homepage":"https://github.com/benywon/ChiQA","introduced_date":"2022-08-05","introduced_date_note":null,"introduced_by":{"paper":"/paper/chiqa-a-large-scale-image-based-real-world","title":"ChiQA: A Large Scale Image-based Real-World Question Answering Dataset for Multi-Modal Understanding","first_author":"Bingning Wang","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"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":["ChiQA"],"data_loaders":[],"num_papers_in_archive":1,"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."}