{"url":"/dataset/videoxum-1","name":"VideoXum","full_name":null,"description_markdown":"VideoXum is an enriched large-scale dataset for cross-modal video summarization.\r\nThe dataset is built on ActivityNet Captions. The datasets includes three subtasks: Video-to-Video Summarization (V2V-SUM), Video-to-Text Summarization (V2T-SUM), and Video-to-Video&Text Summarization (V2VT-SUM).","description_withheld":null,"homepage":"https://videoxum.github.io/","introduced_date":"2023-03-21","introduced_date_note":null,"introduced_by":{"paper":"/paper/videoxum-cross-modal-visual-and-textural","title":"VideoXum: Cross-modal Visual and Textural Summarization of Videos","first_author":"Jingyang Lin","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Video Summarization","url":"/task/video-summarization","datasets_with_task":"/datasets/task/video-summarization"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["VideoXum"],"data_loaders":[],"num_papers_in_archive":8,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/video-summarization-on-videoxum","task":"Video Summarization","dataset_variant":"videoxum","rows":1,"metrics":["1 shot Micro-F1"],"first_row_in_archive_order":{"model":"VTSUM-BLIP","paper":"/paper/videoxum-cross-modal-visual-and-textural","metrics":{"1 shot Micro-F1":"23.5"},"code_links":[{"title":"jylins/videoxum","url":"https://github.com/jylins/videoxum"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/videoxum-cross-modal-visual-and-textural","title":"VideoXum: Cross-modal Visual and Textural Summarization of Videos","date":"2023-03-21","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"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."}