{"url":"/dataset/internvid","name":"InternVid","full_name":null,"description_markdown":"**InternVid** is a large-scale video-centric multimodal dataset that enables learning powerful and transferable video-text representations for multimodAL understanding and generation. The InternVid dataset contains over 7 million videos lasting nearly 760K hours, yielding 234M video clips accompanied by detailed descriptions of total 4.1B words.","description_withheld":null,"homepage":"https://github.com/OpenGVLab/InternVideo/tree/main/Data/InternVid","introduced_date":"2023-07-13","introduced_date_note":null,"introduced_by":{"paper":"/paper/internvid-a-large-scale-video-text-dataset","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","first_author":"Yi Wang","url":null},"license":{"name":"Apache-2.0 license","url":"https://github.com/OpenGVLab/InternVideo/blob/main/LICENSE"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Video Understanding","url":"/task/video-understanding","datasets_with_task":"/datasets/task/video-understanding"},{"name":"Video Generation","url":"/task/video-generation","datasets_with_task":"/datasets/task/video-generation"}],"languages":[],"variants":["InternVid"],"data_loaders":[],"num_papers_in_archive":46,"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."}