{"url":"/dataset/openvidial","name":"OpenViDial","full_name":null,"description_markdown":"**OpenViDial** is a large-scale open-domain dialogue dataset with visual contexts. The dialogue turns and visual contexts are extracted from movies and TV series, where each dialogue turn is paired with the corresponding visual context in which it takes place. OpenViDial contains a total number of 1.1 million dialogue turns, and thus 1.1 million visual contexts stored in images.\n\nSource: [https://github.com/ShannonAI/OpenViDial](https://github.com/ShannonAI/OpenViDial)\nImage Source: [https://github.com/ShannonAI/OpenViDial](https://github.com/ShannonAI/OpenViDial)","description_withheld":null,"homepage":"https://github.com/ShannonAI/OpenViDial","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/openvidial-a-large-scale-open-domain-dialogue","title":"OpenViDial: A Large-Scale, Open-Domain Dialogue Dataset with Visual Contexts","first_author":"Yuxian Meng","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Dialogue Generation","url":"/task/dialogue-generation","datasets_with_task":"/datasets/task/dialogue-generation"}],"languages":[],"variants":["OpenViDial"],"data_loaders":[{"repo":"https://github.com/ShannonAI/OpenViDial","url":"https://github.com/ShannonAI/OpenViDial","frameworks":["pytorch"]}],"num_papers_in_archive":8,"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."}