{"url":"/dataset/stanford40","name":"Stanford40","full_name":"Stanford 40 Actions","description_markdown":"The Stanford 40 Action Dataset contains images of humans performing 40 actions. In each image, we provide a bounding box of the person who is performing the action indicated by the filename of the image. There are 9532 images in total with 180-300 images per action class.","description_withheld":null,"homepage":"http://vision.stanford.edu/Datasets/40actions.html","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Activity Recognition","url":"/task/activity-recognition","datasets_with_task":"/datasets/task/activity-recognition"}],"languages":[],"variants":["Stanford40"],"data_loaders":[],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/activity-recognition-on-stanford40","task":"Activity Recognition","dataset_variant":"Stanford40","rows":2,"metrics":["Top-3 Accuracy (%)"],"first_row_in_archive_order":{"model":"FocusCLIP","paper":"/paper/focusclip-multimodal-subject-level-guidance","metrics":{"Top-3 Accuracy (%)":"10.47"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/focusclip-multimodal-subject-level-guidance","title":"Human Pose Descriptions and Subject-Focused Attention for Improved Zero-Shot Transfer in Human-Centric Classification Tasks","date":"2024-03-11","rows_on_this_dataset":2,"code_links":0,"syntology":null}],"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."}