NTU RGB+D 120

Introduced by Liu et al. in NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding

NTU RGB+D 120 is 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 daily, mutual, and health-related activities.

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

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Skeleton Based Action Recognition	NTU RGB+D 120	DeGCN
Action Recognition	NTU RGB+D 120	PoseC3D
One-Shot 3D Action Recognition	NTU RGB+D 120	MotionBERT
Human Interaction Recognition	NTU RGB+D 120	SkateFormer
Unsupervised Skeleton Based Action Recognition	NTU RGB+D 120	BRL
Generalized Zero Shot skeletal action recognition	NTU RGB+D 120	MSF-GZSSAR
Human action generation	NTU RGB+D 120	c-GAN
Zero Shot Skeletal Action Recognition	NTU RGB+D 120	SynSE