{"url":"/dataset/utd-mhad","name":"UTD-MHAD","full_name":null,"description_markdown":"The **UTD-MHAD** dataset consists of 27 different actions performed by 8 subjects. Each subject repeated the action for 4 times, resulting in 861 action sequences in total. The RGB, depth, skeleton and the inertial sensor signals were recorded.\r\n\r\nSource: [Skepxels: Spatio-temporal Image Representation of Human Skeleton Joints for Action Recognition](https://arxiv.org/abs/1711.05941)\r\nImage Source: [https://www.researchgate.net/figure/Sample-shots-of-the-27-actions-in-the-UTD-MHAD-database_fig12_283090976](https://www.researchgate.net/figure/Sample-shots-of-the-27-actions-in-the-UTD-MHAD-database_fig12_283090976)","description_withheld":null,"homepage":"https://www.utdallas.edu/~kehtar/UTD-MHAD.html","introduced_date":"2015-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"UTD-MHAD: A multimodal dataset for human action recognition utilizing a depth camera and a wearable inertial sensor","first_author":null,"url":"https://doi.org/10.1109/ICIP.2015.7350781"},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Action Recognition","url":"/task/action-recognition-in-videos","datasets_with_task":"/datasets/task/action-recognition-in-videos"},{"name":"Temporal Action Localization","url":"/task/action-recognition","datasets_with_task":"/datasets/task/action-recognition"},{"name":"Multimodal Activity Recognition","url":"/task/multimodal-activity-recognition","datasets_with_task":"/datasets/task/multimodal-activity-recognition"}],"languages":[],"variants":["UTD-MHAD"],"data_loaders":[],"num_papers_in_archive":62,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/multimodal-activity-recognition-on-utd-mhad","task":"Multimodal Activity Recognition","dataset_variant":"UTD-MHAD","rows":5,"metrics":["Accuracy (CS)"],"first_row_in_archive_order":{"model":"PoseMap","paper":"/paper/recognizing-human-actions-as-the-evolution-of","metrics":{"Accuracy (CS)":"94.5"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/action-recognition-in-videos-on-utd-mhad","task":"Action Recognition","dataset_variant":"UTD-MHAD","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Action Machine (RGB only)","paper":"/paper/action-machine-rethinking-action-recognition","metrics":{"Accuracy":"92.5"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/gimme-signals-discriminative-signal-encoding","title":"Gimme Signals: Discriminative signal encoding for multimodal activity recognition","date":"2020-03-13","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/bayesian-hierarchical-dynamic-model-for-human","title":"Bayesian Hierarchical Dynamic Model for Human Action Recognition","date":"2019-06-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/star-net-action-recognition-using-spatio","title":"STAR-Net: Action Recognition using Spatio-Temporal Activation Reprojection","date":"2019-02-26","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/action-machine-rethinking-action-recognition","title":"Action Machine: Rethinking Action Recognition in Trimmed Videos","date":"2018-12-14","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/recognizing-human-actions-as-the-evolution-of","title":"Recognizing Human Actions as the Evolution of Pose Estimation Maps","date":"2018-06-01","rows_on_this_dataset":1,"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."}