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.
@article{arxiv.2105.01563,
title = {Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition},
author = {Zhenyue Qin and Yang Liu and Pan Ji and Dongwoo Kim and Lei Wang and Bob McKay and Saeed Anwar and Tom Gedeon},
journal= {arXiv preprint arXiv:2105.01563},
year = {2022}
}
Comments
Accepted by IEEE Transactions on Neural Networks and Learning Systems