Spatio-Temporal Difference Descriptor for Skeleton-Based Action Recognition
Keywords:Video Understanding & Activity Analysis
AbstractIn skeletal representation, intra-frame differences between body joints, as well as inter-frame dynamics between body skeletons contain discriminative information for action recognition. Conventional methods for modeling human skeleton sequences generally depend on motion trajectory and body joint dependency information, thus lacking the ability to identify the inherent differences of human skeletons. In this paper, we propose a spatio-temporal difference descriptor based on a directional convolution architecture that enables us to learn the spatio-temporal differences and contextual dependencies between different body joints simultaneously. The overall model is built on a deep symmetric positive definite (SPD) metric learning architecture designed to learn discriminative manifold features with the well-designed non-linear mapping operation. Experiments on several action datasets show that our proposed method achieves up to 3% accuracy improvement over state-of-the-art methods.
How to Cite
Ding, C., Liu, K., Korhonen, J., & Belyaev, E. (2021). Spatio-Temporal Difference Descriptor for Skeleton-Based Action Recognition. Proceedings of the AAAI Conference on Artificial Intelligence, 35(2), 1227-1235. https://doi.org/10.1609/aaai.v35i2.16210
AAAI Technical Track on Computer Vision I