{"url":"/dataset/cad-120","name":"CAD-120","full_name":null,"description_markdown":"The CAD-60 and **CAD-120** data sets comprise of RGB-D video sequences of humans performing activities which are recording using the Microsoft Kinect sensor. Being able to detect human activities is important for making personal assistant robots useful in performing assistive tasks. The CAD dataset comprises twelve different activities (composed of several sub-activities) performed by four people in different environments, such as a kitchen, a living room, and office, etc.\r\n\r\nSource: [https://www.re3data.org/repository/r3d100012216](https://www.re3data.org/repository/r3d100012216)\r\nImage Source: [https://www.researchgate.net/figure/The-CAD-120-dataset-A-Examples-of-high-level-activities-from-the-dataset-B-A_fig3_335424041](https://www.researchgate.net/figure/The-CAD-120-dataset-A-Examples-of-high-level-activities-from-the-dataset-B-A_fig3_335424041)","description_withheld":null,"homepage":"https://www.re3data.org/repository/r3d100012216","introduced_date":"2013-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/learning-human-activities-and-object","title":"Learning Human Activities and Object Affordances from RGB-D Videos","first_author":"Hema Swetha Koppula","url":null},"license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"},{"name":"RGB-D","url":"/datasets/modality/rgb-d"}],"tasks":[{"name":"Skeleton Based Action Recognition","url":"/task/skeleton-based-action-recognition","datasets_with_task":"/datasets/task/skeleton-based-action-recognition"}],"languages":[],"variants":["CAD-120"],"data_loaders":[{"repo":"https://github.com/Shimingyi/MotioNet","url":"https://github.com/Shimingyi/MotioNet","frameworks":["pytorch"]}],"num_papers_in_archive":65,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/skeleton-based-action-recognition-on-cad-120","task":"Skeleton Based Action Recognition","dataset_variant":"CAD-120","rows":8,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"NGM (5-shot)","paper":"/paper/neural-graph-matching-networks-for-fewshot-3d","metrics":{"Accuracy":"91.1%"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/neural-graph-matching-networks-for-fewshot-3d","title":"Neural Graph Matching Networks for Fewshot 3D Action Recognition","date":"2018-09-01","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/pointnet-deep-learning-on-point-sets-for-3d","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","date":"2016-12-02","rows_on_this_dataset":1,"code_links":110,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":164,"samples_ran":89,"samples_unverified":75,"pointer_only_for_licence":90,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/ntu-rgbd-a-large-scale-dataset-for-3d-human","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","date":"2016-04-11","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/structural-rnn-deep-learning-on-spatio","title":"Structural-RNN: Deep Learning on Spatio-Temporal Graphs","date":"2015-11-17","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-spatio-temporal-structure-from-rgb-d","title":"Learning Spatio-Temporal Structure from RGB-D Videos for Human Activity Detection and Anticipation","date":"2013-02-01","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/learning-human-activities-and-object","title":"Learning Human Activities and Object Affordances from RGB-D Videos","date":"2012-10-04","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":165,"samples_ran":89,"samples_unverified":76,"pointer_only_for_licence":90,"papers_with_no_sample_that_ran":1,"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."}