3D Action Recognition
29 papers with code • 2 benchmarks • 13 datasets
Image: Rahmani et al
Over the last decade, Convolutional Neural Network (CNN) models have been highly successful in solving complex vision problems.
Spatial-temporal graphs have been widely used by skeleton-based action recognition algorithms to model human action dynamics.
In addition, the second-order information (the lengths and directions of bones) of the skeleton data, which is naturally more informative and discriminative for action recognition, is rarely investigated in existing methods.
One primary technical challenge in photoacoustic microscopy (PAM) is the necessary compromise between spatial resolution and imaging speed.
Recent approaches in depth-based human activity analysis achieved outstanding performance and proved the effectiveness of 3D representation for classification of action classes.
In this work, we propose to use a new class of models known as Temporal Convolutional Neural Networks (TCN) for 3D human action recognition.
The proposed method achieved state-of-the-art performance on NTU RGB+D dataset for 3D human action analysis.
This method introduces the definition of body states and then every action is modeled as a sequence of these states.
The proposed regularized Mahalanobis distance metric is used in order to recognize both the involuntary and highly made-up actions at the same time.