{"url":"/dataset/ego4d-hcap","name":"Ego4D-HCap","full_name":null,"description_markdown":"Ego4D-HCap is a hierarchical video captioning dataset comprised of a three-tier hierarchy of captions: short clip-level captions, medium-length video segment descriptions, and long-range video-level summaries. To construct Ego4D-HCap, we leverage Ego4D, the largest publicly available egocentric video dataset. While Ego4D comes with time-stamped atomic captions and video-segment descriptions spanning up to 5 minutes, it lacks video-level summaries for longer video durations. To address this issue, we annotate a subset of 8,267 Ego4D videos with long-range video summaries, each spanning up to two hours. This enhancement provides a three-level hierarchy of captions.","description_withheld":null,"homepage":"https://sites.google.com/view/vidrecap","introduced_date":"2024-02-20","introduced_date_note":null,"introduced_by":{"paper":"/paper/video-recap-recursive-captioning-of-hour-long","title":"Video ReCap: Recursive Captioning of Hour-Long Videos","first_author":"Md Mohaiminul Islam","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":["Ego4D-HCap"],"data_loaders":[],"num_papers_in_archive":3,"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."}