Action Capsules: Human Skeleton Action Recognition
This work addresses a bottleneck in skeleton-based action recognition for applications like surveillance or human-computer interaction, representing an incremental improvement over existing methods.
The paper tackles the challenge of encoding global joint dependencies in skeleton-based human action recognition by introducing Action Capsules, which identify action-related key joints and aggregate their features, resulting in state-of-the-art performance on the N-UCLA dataset and competitive results on the NTURGBD dataset with lower computational costs.
Due to the compact and rich high-level representations offered, skeleton-based human action recognition has recently become a highly active research topic. Previous studies have demonstrated that investigating joint relationships in spatial and temporal dimensions provides effective information critical to action recognition. However, effectively encoding global dependencies of joints during spatio-temporal feature extraction is still challenging. In this paper, we introduce Action Capsule which identifies action-related key joints by considering the latent correlation of joints in a skeleton sequence. We show that, during inference, our end-to-end network pays attention to a set of joints specific to each action, whose encoded spatio-temporal features are aggregated to recognize the action. Additionally, the use of multiple stages of action capsules enhances the ability of the network to classify similar actions. Consequently, our network outperforms the state-of-the-art approaches on the N-UCLA dataset and obtains competitive results on the NTURGBD dataset. This is while our approach has significantly lower computational requirements based on GFLOPs measurements.