NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding

Liu, Jun; Shahroudy, Amir; Pérez, Mauricio; Wang, Gang; Duan, Ling‐Yu; Kot, Alex C.

doi:10.1109/tpami.2019.2916873

articleIEEE Transactions on Pattern Analysis and Machine IntelligenceMay 14, 2019GREEN OA

NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding

JLJun Liu ASAmir Shahroudy MPMauricio Pérez GWGang Wang LDLing‐Yu Duan

Nanyang Technological University · Chalmers University of Technology · +3 more institutions

PubMed

Indexed inarxivcrossrefpubmed

Abstract

Research on depth-based human activity analysis achieved outstanding performance and demonstrated the effectiveness of 3D representation for action recognition. The existing depth-based and RGB+D-based action recognition benchmarks have a number of limitations, including the lack of large-scale training samples, realistic number of distinct class categories, diversity in camera views, varied environmental conditions, and variety of human subjects. In this work, we introduce a large-scale dataset for RGB+D human action recognition, which is collected from 106 distinct subjects and contains more than 114 thousand video samples and 8 million frames. This dataset contains 120 different action classes including…

Citation impact

1,711

total citations

FWCI: 55.83
Percentile: 100%
References: 138

Citations per year

Authors

6

Topics & keywords

Topics

Keywords

Benchmark (surveying)
Artificial intelligence
Computer science
Scale (ratio)
RGB color model
Computer vision
Machine learning
Pattern recognition (psychology)

No related works found for this paper.