{"url":"/dataset/kinetics-400-1","name":"Kinetics 400","full_name":null,"description_markdown":"The dataset contains 400 human action classes, with at least 400 video clips for each action. Each clip lasts around 10s and is taken from a different YouTube video. The actions are human focussed and cover a broad range of classes including human-object interactions such as playing instruments, as well as human-human interactions such as shaking hands.\r\n\r\nSource: [https://arxiv.org/abs/1705.06950](https://arxiv.org/abs/1705.06950)\r\n\r\nImage source: [https://arxiv.org/abs/1705.06950](https://arxiv.org/abs/1705.06950)","description_withheld":null,"homepage":"https://deepmind.com/research/open-source/kinetics","introduced_date":"2017-05-19","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-kinetics-human-action-video-dataset","title":"The Kinetics Human Action Video Dataset","first_author":"Will Kay","url":null},"license":{"name":"Creative Commons Attribution 4.0 International License","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Skeleton Based Action Recognition","url":"/task/skeleton-based-action-recognition","datasets_with_task":"/datasets/task/skeleton-based-action-recognition"},{"name":"Action Classification","url":"/task/action-classification","datasets_with_task":"/datasets/task/action-classification"},{"name":"Action Recognition In Videos","url":"/task/action-recognition-in-videos-2","datasets_with_task":"/datasets/task/action-recognition-in-videos-2"},{"name":"Boundary Detection","url":"/task/boundary-detection","datasets_with_task":"/datasets/task/boundary-detection"},{"name":"Self-Supervised Action Recognition","url":"/task/self-supervised-action-recognition","datasets_with_task":"/datasets/task/self-supervised-action-recognition"},{"name":"Event Segmentation","url":"/task/event-segmentation","datasets_with_task":"/datasets/task/event-segmentation"},{"name":"Self-Supervised Action Recognition Linear","url":"/task/self-supervised-action-recognition-linear","datasets_with_task":"/datasets/task/self-supervised-action-recognition-linear"}],"languages":[],"variants":["Kinetics-400","Kinetics 400"],"data_loaders":[{"repo":"https://github.com/pytorch/vision","url":"https://pytorch.org/vision/stable/generated/torchvision.datasets.Kinetics400.html","frameworks":["pytorch"]},{"repo":"https://github.com/voxel51/fiftyone","url":"https://docs.voxel51.com/user_guide/dataset_zoo/datasets.html#kinetics-400","frameworks":["tf","pytorch"]}],"num_papers_in_archive":712,"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."}