Skeleton-based action recognition has attracted considerable attention due to its compact representation of the human body’s skeletal structure. Many recent methods have achieved remarkable performance using graph convoluitional networks (GCNs) and convolutional neural networks (CNNs), which extract spatial and temporal features, respectively. Although spatial and temporal dependencies in the human skeleton have been explored separately, spatio-temporal dependency is rarely considered.

Skeleton-based action recognition has attracted considerable attention due to its compact representation of the human body’s skeletal structure. Many recent methods have achieved remarkable performance using graph convoluitional networks (GCNs) and convolutional neural networks (CNNs), which extract spatial and temporal features, respectively. Although spatial and temporal dependencies in the human skeleton have been explored separately, spatio-temporal dependency is rarely considered.

Skeleton-based action recognition has attracted considerable attention due to its compact representation of the human body’s skeletal structure. Many recent methods have achieved remarkable performance using graph convoluitional networks (GCNs) and convolutional neural networks (CNNs), which extract spatial and temporal features, respectively. Although spatial and temporal dependencies in the human skeleton have been explored separately, spatio-temporal dependency is rarely considered.

Skeleton-based action recognition has attracted considerable attention due to its compact representation of the human body’s skeletal structure. Many recent methods have achieved remarkable performance using graph convoluitional networks (GCNs) and convolutional neural networks (CNNs), which extract spatial and temporal features, respectively. Although spatial and temporal dependencies in the human skeleton have been explored separately, spatio-temporal dependency is rarely considered.