Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition

TL;DR

This paper introduces a method to improve skeleton-based action recognition by fusing higher-order angular features into graph neural networks, achieving state-of-the-art accuracy with fewer parameters.

Contribution

It proposes a novel angular encoding technique for higher-order features, enhancing the robustness and accuracy of existing graph neural network architectures for action recognition.

Findings

Achieves new state-of-the-art accuracy on NTU60 and NTU120 benchmarks.

Uses fewer parameters and reduces runtime compared to previous methods.

Effectively captures relationships between joints and body parts.

Abstract

Skeleton sequences are lightweight and compact, and thus are ideal candidates for action recognition on edge devices. Recent skeleton-based action recognition methods extract features from 3D joint coordinates as spatial-temporal cues, using these representations in a graph neural network for feature fusion to boost recognition performance. The use of first- and second-order features, i.e., joint and bone representations, has led to high accuracy. Nonetheless, many models are still confused by actions that have similar motion trajectories. To address these issues, we propose fusing higher-order features in the form of angular encoding into modern architectures to robustly capture the relationships between joints and body parts. This simple fusion with popular spatial-temporal graph neural networks achieves new state-of-the-art accuracy in two large benchmarks, including NTU60 and NTU120, while employing fewer parameters and reduced run time. Our source code is publicly available at: https://github.com/ZhenyueQin/Angular-Skeleton-Encoding.