Hierarchical Human Action Classification with Network Pruning

Research on human action classification has made significant progresses in the past few years. Most deep learning methods focus on improving performance by adding more network components. We propose, however, to better utilize auxiliary mechanisms, including hierarchical classification, network pruning, and skeleton-based preprocessing, to boost the model robustness and performance. We test the effectiveness of our method on three commonly used testing datasets: NTU RGB+D 60, NTU RGB+D 120, and Northwestern-UCLA Multiview Action 3D. Our experiments show that our method can achieve either comparable or better performance than state-of-the-art methods on all three datasets. In particular, our method sets up a new baseline for NTU 120, the largest dataset among the three. We also analyze our method with extensive comparisons and ablation studies.