{"url":"/dataset/hourvideo","name":"HourVideo","full_name":null,"description_markdown":"We introduce HourVideo, a benchmark dataset for hour-long video-language understanding. HourVideo consists of a novel task suite comprising summarization, perception (*recall, tracking*), visual reasoning (*spatial, temporal, predictive, causal, counterfactual*), and navigation (*room-to-room, object retrieval*) tasks. HourVideo includes **500 manually curated egocentric videos** from the Ego4D dataset, spanning durations of **20 to 120 minutes**, and features **12,976 high-quality, five-way multiple-choice questions**. We hope to establish HourVideo as a benchmark challenge to spur the development of advanced multimodal models capable of truly understanding endless streams of visual data.","description_withheld":null,"homepage":"https://hourvideo.stanford.edu","introduced_date":"2024-12-02","introduced_date_note":null,"introduced_by":{"paper":"/paper/hourvideo-1-hour-video-language-understanding","title":"HourVideo: 1-Hour Video-Language Understanding","first_author":"Keshigeyan Chandrasegaran","url":null},"license":{"name":"Apache License, Version 2.0","url":"https://opensource.org/license/apache-2-0"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["HourVideo"],"data_loaders":[],"num_papers_in_archive":5,"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."}