{"url":"/dataset/tsu","name":"TSU","full_name":"Toyota Smarthome Untrimmed","description_markdown":"Toyota Smarthome Untrimmed (TSU) is a dataset for activity detection in long untrimmed videos. The dataset contains 536 videos with an average duration of 21 mins. Since this dataset is based on the same footage video as Toyota Smarthome Trimmed version, it features the same challenges and introduces additional ones. The dataset is annotated with 51 activities.\r\n\r\nThe dataset has been recorded in an apartment equipped with 7 Kinect v1 cameras. It contains common daily living activities of 18 subjects. The subjects are senior people in the age range 60-80 years old. The dataset has a resolution of 640×480 and offers 3 modalities: RGB + Depth + 3D Skeleton. The 3D skeleton joints were extracted from RGB. For privacy-preserving reasons, the face of the subjects is blurred.\r\n\r\nSource: [Toyota Smarthome](https://project.inria.fr/toyotasmarthome/)","description_withheld":null,"homepage":"https://project.inria.fr/toyotasmarthome/","introduced_date":"2020-10-28","introduced_date_note":null,"introduced_by":{"paper":"/paper/toyota-smarthome-untrimmed-real-world","title":"Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detection","first_author":"Rui Dai","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":"Activity Detection","url":"/task/activity-detection","datasets_with_task":"/datasets/task/activity-detection"}],"languages":[],"variants":["TSU"],"data_loaders":[{"repo":"https://github.com/dairui01/Toyota_Smarthome","url":"https://project.inria.fr/toyotasmarthome/","frameworks":["pytorch"]}],"num_papers_in_archive":16,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/action-detection-on-tsu","task":"Action Detection","dataset_variant":"TSU","rows":2,"metrics":["Frame-mAP"],"first_row_in_archive_order":{"model":"PDAN","paper":"/paper/pdan-pyramid-dilated-attention-network-for","metrics":{"Frame-mAP":"32.7"},"code_links":[{"title":"dairui01/PDAN","url":"https://github.com/dairui01/PDAN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/ms-tct-multi-scale-temporal-convtransformer","title":"MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection","date":"2021-12-07","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pdan-pyramid-dilated-attention-network-for","title":"PDAN: Pyramid Dilated Attention Network for Action Detection","date":"2021-01-05","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":1,"samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"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."}