{"url":"/dataset/mlb-youtube-dataset","name":"MLB-YouTube Dataset","full_name":null,"description_markdown":"The MLB-YouTube dataset is a new, large-scale dataset consisting of 20 baseball games from the 2017 MLB post-season available on YouTube with over 42 hours of video footage. The dataset consists of two components: segmented videos for activity recognition and continuous videos for activity classification. It is quite challenging as it is created from TV broadcast baseball games where multiple different activities share the camera angle. Further, the motion/appearance difference between the various activities is quite small.\n\nSource: [https://github.com/piergiaj/mlb-youtube](https://github.com/piergiaj/mlb-youtube)\nImage Source: [https://github.com/piergiaj/mlb-youtube](https://github.com/piergiaj/mlb-youtube)","description_withheld":null,"homepage":"https://github.com/piergiaj/mlb-youtube","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/fine-grained-activity-recognition-in-baseball","title":"Fine-grained Activity Recognition in Baseball Videos","first_author":"AJ Piergiovanni","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Action Detection","url":"/task/action-detection","datasets_with_task":"/datasets/task/action-detection"},{"name":"Video Understanding","url":"/task/video-understanding","datasets_with_task":"/datasets/task/video-understanding"},{"name":"Activity Detection","url":"/task/activity-detection","datasets_with_task":"/datasets/task/activity-detection"}],"languages":[],"variants":["MLB-YouTube Dataset"],"data_loaders":[{"repo":"https://github.com/piergiaj/mlb-youtube","url":"https://github.com/piergiaj/mlb-youtube","frameworks":["pytorch"]}],"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."}