{"url":"/dataset/openvidial-2-0","name":"OpenViDial 2.0","full_name":null,"description_markdown":"OpenViDial 2.0 is a larger-scale open-domain multi-modal dialogue dataset compared to the previous version [OpenViDial 1.0](/dataset/openvidial). OpenViDial 2.0 contains a total number of 5.6 million dialogue turns extracted from either movies or TV series from different resources, and each dialogue turn is paired with its corresponding visual context. \r\n\r\nImage source: [https://github.com/ShannonAI/OpenViDial](https://github.com/ShannonAI/OpenViDial)","description_withheld":null,"homepage":"https://github.com/ShannonAI/OpenViDial","introduced_date":"2021-09-27","introduced_date_note":null,"introduced_by":{"paper":"/paper/openvidial-2-0-a-larger-scale-open-domain","title":"OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts","first_author":"Shuhe Wang","url":null},"license":{"name":"Unknown","url":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"},{"name":"Multi-modal Dialogue Generation","url":"/task/multi-modal-dialogue-generation","datasets_with_task":"/datasets/task/multi-modal-dialogue-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["OpenViDial 2.0"],"data_loaders":[{"repo":"https://github.com/ShannonAI/OpenViDial","url":"https://github.com/ShannonAI/OpenViDial","frameworks":[]}],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/multi-modal-dialogue-generation-on-openvidial","task":"Multi-modal Dialogue Generation","dataset_variant":"OpenViDial 2.0","rows":4,"metrics":["BLEU","Dis-1","Dis-2","Dis-3","Dis-4"],"first_row_in_archive_order":{"model":"FV (w/o MI)","paper":"/paper/openvidial-2-0-a-larger-scale-open-domain","metrics":{"BLEU":"1.99","Dis-1":"0.0056","Dis-2":"0.0431","Dis-3":"0.125","Dis-4":"0.2215"},"code_links":[{"title":"ShannonAI/OpenViDial","url":"https://github.com/ShannonAI/OpenViDial"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/openvidial-2-0-a-larger-scale-open-domain","title":"OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts","date":"2021-09-27","rows_on_this_dataset":4,"code_links":1,"syntology":null}],"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."}