{"url":"/dataset/toyota-smarthome","name":"Toyota Smarthome Dataset","full_name":null,"description_markdown":"A large scale dataset with daily-living activities performed in a natural manner.\r\n\r\nSource: [Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detection](/paper/toyota-smarthome-untrimmed-real-world)","description_withheld":null,"homepage":"https://project.inria.fr/toyotasmarthome/","introduced_date":"2022-05-01","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":"Action Classification","url":"/task/action-classification","datasets_with_task":"/datasets/task/action-classification"},{"name":"Activity Detection","url":"/task/activity-detection","datasets_with_task":"/datasets/task/activity-detection"}],"languages":[],"variants":["TSU","Toyota Smarthome Dataset","Toyota Smarthome dataset"],"data_loaders":[{"repo":"https://github.com/dairui01/Toyota_Smarthome","url":"https://github.com/dairui01/Toyota_Smarthome","frameworks":[]}],"num_papers_in_archive":31,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/action-classification-on-toyota-smarthome","task":"Action Classification","dataset_variant":"Toyota Smarthome dataset","rows":13,"metrics":["CS","CV1","CV2","Accuracy"],"first_row_in_archive_order":{"model":"π-ViT","paper":"/paper/just-add-p-pose-induced-video-transformers","metrics":{"CS":"72.9","CV1":"55.2","CV2":"64.8"},"code_links":[{"title":"dominickrei/pi-vit","url":"https://github.com/dominickrei/pi-vit"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/epam-net-an-efficient-pose-driven-attention","title":"EPAM-Net: An Efficient Pose-driven Attention-guided Multimodal Network for Video Action Recognition","date":"2024-08-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/just-add-p-pose-induced-video-transformers","title":"Just Add $π$! Pose Induced Video Transformers for Understanding Activities of Daily Living","date":"2023-11-30","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mmnet-a-model-based-multimodal-network-for","title":"MMNet: A Model-Based Multimodal Network for Human Action Recognition in RGB-D Videos","date":"2022-05-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/proformer-learning-data-efficient","title":"Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions","date":"2022-02-23","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/unik-a-unified-framework-for-real-world","title":"UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition","date":"2021-07-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/adaptive-intermediate-representations-for","title":"Adaptive Intermediate Representations for Video Understanding","date":"2021-04-14","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/recognizing-actions-in-videos-from-unseen","title":"Recognizing Actions in Videos from Unseen Viewpoints","date":"2021-03-30","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/assemblenet-assembling-modality","title":"AssembleNet++: Assembling Modality Representations via Attention Connections","date":"2020-08-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vpn-learning-video-pose-embedding-for","title":"VPN: Learning Video-Pose Embedding for Activities of Daily Living","date":"2020-07-06","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/toyota-smarthome-real-world-activities-of","title":"Toyota Smarthome: Real-World Activities of Daily Living","date":"2019-10-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/non-local-neural-networks","title":"Non-local Neural Networks","date":"2017-11-21","rows_on_this_dataset":1,"code_links":32,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/quo-vadis-action-recognition-a-new-model-and","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","date":"2017-05-22","rows_on_this_dataset":1,"code_links":34,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":28,"samples_ran":16,"samples_unverified":12,"pointer_only_for_licence":7,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/improved-dense-trajectory-with-cross-streams","title":"Improved Dense Trajectory with Cross Streams","date":"2016-04-29","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":32,"samples_ran":19,"samples_unverified":13,"pointer_only_for_licence":11,"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."}