Progressive Spatio-Temporal Graph Convolutional Network for Skeleton-Based Human Action Recognition
This addresses the need for efficient action recognition in low computation scenarios, such as mobile or embedded systems, by reducing computational costs while maintaining performance.
The paper tackles the problem of high computational complexity in graph convolutional networks (GCNs) for skeleton-based human action recognition by proposing a method to automatically find a compact and problem-specific topology in a progressive manner, achieving competitive or better classification performance with much lower computational complexity on two widely used datasets.
Graph convolutional networks (GCNs) have been very successful in skeleton-based human action recognition where the sequence of skeletons is modeled as a graph. However, most of the GCN-based methods in this area train a deep feed-forward network with a fixed topology that leads to high computational complexity and restricts their application in low computation scenarios. In this paper, we propose a method to automatically find a compact and problem-specific topology for spatio-temporal graph convolutional networks in a progressive manner. Experimental results on two widely used datasets for skeleton-based human action recognition indicate that the proposed method has competitive or even better classification performance compared to the state-of-the-art methods with much lower computational complexity.