Action recognition using part and attention enhanced feature fusion

In various studies on skeleton-based action recognition, graph convolution has been widely used to extract crucial skeleton information. However, existing methods often face challenges in effectively capturing the motion relationships between distinct body parts, such as the coordination between the torso and limbs. To address these limitations, this paper constructs a novel Part and Attention enhanced Feature Fusion Network (PAFFNet). First, we construct center-of-gravity dynamics within semantic body parts to enhance motion representation and capture dynamic trends. Additionally, we design Joint-based Feature Fusion (JFF) stream and Bone-based Feature Fusion (BFF) stream to extract and fuse complementary information between constructed local parted and global skeleton features for enhanced motion representation. Furthermore, an Improved Adaptive Graph Convolution (IAGC) block with denoising and attention mechanisms is proposed to prioritize critical semantic features. Experiments conducted on the NTU RGB+D and Kinetics-Skeleton datasets demonstrate the effectiveness of PAFFNet in improving skeleton-based action recognition.