{"url":"/dataset/webvidvqa3m","name":"WebVidVQA3M","full_name":"WebVidVQA3M","description_markdown":"A dataset automatically generated using question generation neural models and alt-text video captions from the WebVid dataset, with 3M video-question-answer triplets.","description_withheld":null,"homepage":"https://antoyang.github.io/just-ask.html","introduced_date":"2022-05-10","introduced_date_note":null,"introduced_by":{"paper":"/paper/learning-to-answer-visual-questions-from-web","title":"Learning to Answer Visual Questions from Web Videos","first_author":"Antoine Yang","url":null},"license":{"name":"Apache 2.0","url":"https://github.com/antoyang/just-ask/blob/main/LICENSE"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"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":["WebVidVQA3M"],"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."}