TE-STGCN: Topology enhanced spatio-temporal graph convolutional network for skeleton-based action recognition

Key Points

• Action recognition improves using spatio-temporal graph convolutional networks, emphasizing topology enhancement.
• The model showed a notable increase in accuracy, achieving 92% on benchmark datasets including NTU RGB+D.
• Analysis using advanced algorithms highlights the effectiveness of topology enhancement in deep learning frameworks.
• The framework indicates potential for applications in real-time monitoring; application in diverse environments may be needed.