3D Action Recognition On Ntu Rgb D 1

Cross Subject Accuracy

Cross View Accuracy

Results

Performance results of various models on this benchmark

			Paper Title
Kinet	92.3	96.4	No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time Surfaces
PSTNet++	91.4	96.7	Deep Hierarchical Representation of Point Cloud Videos via Spatio-Temporal Decomposition
PSTNet	90.5	96.5	PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences
P4Transformer	90.2	96.4	Point 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud Videos
3DV-PointNet++	88.8	96.3	3DVNet: Multi-View Depth Prediction and Volumetric Refinement

0 of 5 row(s) selected.