A Central Difference Graph Convolutional Operator for Skeleton-Based Action Recognition

TL;DR

This paper introduces a novel central difference graph convolution (CDGC) operator that enhances skeleton-based action recognition by incorporating gradient information, improving efficiency without extra parameters, and demonstrating superior performance on large datasets.

Contribution

The paper presents a new graph convolutional operator, CDGC, that integrates gradient information and can replace vanilla GCNs without additional parameters, along with an accelerated version for faster training.

Findings

Effective on large-scale datasets NTU RGB+D 60 & 120

Improves training speed significantly

Enhances action recognition accuracy

Abstract

This paper proposes a new graph convolutional operator called central difference graph convolution (CDGC) for skeleton based action recognition. It is not only able to aggregate node information like a vanilla graph convolutional operation but also gradient information. Without introducing any additional parameters, CDGC can replace vanilla graph convolution in any existing Graph Convolutional Networks (GCNs). In addition, an accelerated version of the CDGC is developed which greatly improves the speed of training. Experiments on two popular large-scale datasets NTU RGB+D 60 & 120 have demonstrated the efficacy of the proposed CDGC. Code is available at https://github.com/iesymiao/CD-GCN.