{"url":"/dataset/ut-kinect","name":"UT-Kinect","full_name":"UTKinect-Action3D Dataset","description_markdown":"The **UT-Kinect** dataset is a dataset for action recognition from depth sequences. The videos were captured using a single stationary Kinect. There are 10 action types: walk, sit down, stand up, pick up, carry, throw, push, pull, wave hands, clap hands. There are 10 subjects, Each subject performs each actions twice. Three channels were recorded: RGB, depth and skeleton joint locations. The three channel are synchronized. The framerate is 30f/s.\r\n\r\nSource: [https://cvrc.ece.utexas.edu/KinectDatasets/HOJ3D.html](https://cvrc.ece.utexas.edu/KinectDatasets/HOJ3D.html)\r\nImage Source: [https://cvrc.ece.utexas.edu/KinectDatasets/HOJ3D.html](https://cvrc.ece.utexas.edu/KinectDatasets/HOJ3D.html)","description_withheld":null,"homepage":"https://cvrc.ece.utexas.edu/KinectDatasets/HOJ3D.html","introduced_date":"2012-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/view-invariant-human-action-recognition-using","title":"View invariant human action recognition using histograms of 3D joints","first_author":"Lu Xia","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Skeleton Based Action Recognition","url":"/task/skeleton-based-action-recognition","datasets_with_task":"/datasets/task/skeleton-based-action-recognition"},{"name":"Multimodal Activity Recognition","url":"/task/multimodal-activity-recognition","datasets_with_task":"/datasets/task/multimodal-activity-recognition"}],"languages":[],"variants":["UT-Kinect"],"data_loaders":[],"num_papers_in_archive":70,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/skeleton-based-action-recognition-on-ut","task":"Skeleton Based Action Recognition","dataset_variant":"UT-Kinect","rows":7,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Temporal Subspace Clustering","paper":"/paper/subspace-clustering-for-action-recognition","metrics":{"Accuracy":"99.50%"},"code_links":[{"title":"IIT-PAVIS/subspace-clustering-action-recognition","url":"https://github.com/IIT-PAVIS/subspace-clustering-action-recognition"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multimodal-activity-recognition-on-ut-kinect","task":"Multimodal Activity Recognition","dataset_variant":"UT-Kinect","rows":1,"metrics":["Accuracy (CS)"],"first_row_in_archive_order":{"model":"HAMLET","paper":"/paper/hamlet-a-hierarchical-multimodal-attention-1","metrics":{"Accuracy (CS)":"97.56"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/tensor-representations-for-action-recognition","title":"Tensor Representations for Action Recognition","date":"2020-12-28","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/hamlet-a-hierarchical-multimodal-attention-1","title":"HAMLET: A Hierarchical Multimodal Attention-based Human Activity Recognition Algorithm","date":"2020-08-03","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/subspace-clustering-for-action-recognition","title":"Subspace Clustering for Action Recognition with Covariance Representations and Temporal Pruning","date":"2020-06-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/graph-based-skeleton-modeling-for-human","title":"Graph Based Skeleton Modeling for Human Activity Analysis","date":"2019-08-26","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/generalized-graph-convolutional-networks-for","title":"Optimized Skeleton-based Action Recognition via Sparsified Graph Regression","date":"2018-11-29","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/deep-progressive-reinforcement-learning-for","title":"Deep Progressive Reinforcement Learning for Skeleton-Based Action Recognition","date":"2018-06-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/human-action-recognition-by-representing-3d-1","title":"Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group","date":"2014-06-23","rows_on_this_dataset":1,"code_links":1,"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."}