{"url":"/dataset/gqa-rex","name":"GQA-REX","full_name":null,"description_markdown":"A GQA-based dataset with 1,040,830 multi-modal explanations of visual reasoning processes.","description_withheld":null,"homepage":"https://github.com/szzexpoi/rex","introduced_date":"2022-03-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/rex-reasoning-aware-and-grounded-explanation","title":"REX: Reasoning-aware and Grounded Explanation","first_author":"Shi Chen","url":null},"license":{"name":"MIT license","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Explanatory Visual Question Answering","url":"/task/explanatory-visual-question-answering","datasets_with_task":"/datasets/task/explanatory-visual-question-answering"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["GQA-REX"],"data_loaders":[],"num_papers_in_archive":8,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/explanatory-visual-question-answering-on-gqa","task":"Explanatory Visual Question Answering","dataset_variant":"GQA-REX","rows":5,"metrics":["BLEU-4","CIDEr","GQA-test","GQA-val","Grounding","METEOR","ROUGE-L","SPICE"],"first_row_in_archive_order":{"model":"VCIN","paper":"/paper/variational-causal-inference-network-for","metrics":{"BLEU-4":"58.65","CIDEr":"519.23","GQA-test":"60.61","GQA-val":"81.80","Grounding":"77.33","METEOR":"41.57","ROUGE-L":"81.45","SPICE":"54.63"},"code_links":[{"title":"LivXue/VCIN","url":"https://github.com/LivXue/VCIN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/variational-causal-inference-network-for","title":"Variational Causal Inference Network for Explanatory Visual Question Answering","date":"2023-01-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rex-reasoning-aware-and-grounded-explanation","title":"REX: Reasoning-aware and Grounded Explanation","date":"2022-03-11","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/faithful-multimodal-explanation-for-visual","title":"Faithful Multimodal Explanation for Visual Question Answering","date":"2018-09-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vqa-e-explaining-elaborating-and-enhancing","title":"VQA-E: Explaining, Elaborating, and Enhancing Your Answers for Visual Questions","date":"2018-03-20","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":2,"samples_ran":2,"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."}