{"url":"/dataset/vmsmo","name":"VMSMO","full_name":null,"description_markdown":"The Video-based Multimodal Summarization with Multimodal Output (**VMSMO**) corpus consists of 184,920 document-summary pairs, with 180,000 training pairs, 2,460 validation and test pairs. The task for this dataset is generating and appropriate textual summary of an article and choosing a proper cover frame from a video accompanying the article.\n\nSource: [https://github.com/yingtaomj/VMSMO](https://github.com/yingtaomj/VMSMO)","description_withheld":null,"homepage":"https://github.com/yingtaomj/VMSMO","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/vmsmo-learning-to-generate-multimodal-summary","title":"VMSMO: Learning to Generate Multimodal Summary for Video-based News Articles","first_author":"Mingzhe Li","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Reading Comprehension","url":"/task/reading-comprehension","datasets_with_task":"/datasets/task/reading-comprehension"},{"name":"Multi-Task Learning","url":"/task/multi-task-learning","datasets_with_task":"/datasets/task/multi-task-learning"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["VMSMO"],"data_loaders":[{"repo":"https://github.com/yingtaomj/VMSMO","url":"https://github.com/yingtaomj/VMSMO","frameworks":["tf"]}],"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."}