{"url":"/dataset/r2vq","name":"R2VQ","full_name":"Recipe-to-Video Questions","description_markdown":"R2VQ is a dataset designed for testing competence-based comprehension of machines over a multimodal recipe collection, which contains text-video aligned recipes.\r\n\r\nA total of 51,331 cooking events are annotated, which contain 19,201 explicit ingredients, 16,338 implicit ingredients, 12,316 explicit props, and 11,868 implicit props.","description_withheld":null,"homepage":"https://r2vq.org/","introduced_date":"2021-05-12","introduced_date_note":null,"introduced_by":{"paper":"/paper/designing-multimodal-datasets-for-nlp","title":"Designing Multimodal Datasets for NLP Challenges","first_author":"James Pustejovsky","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["R2VQ"],"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."}