Action Recognition with Kernel-based Graph Convolutional Networks

TL;DR

This paper introduces a novel kernel-based graph convolutional network that operates in a high-dimensional space, improving discriminability and permutation invariance for skeleton-based action recognition.

Contribution

It proposes a new GCN framework using RKHS for spatial convolution, avoiding explicit node realignment and reducing overfitting risks.

Findings

Outperforms existing methods on skeleton-based action recognition

Achieves permutation invariance in graph convolutions

Maintains low computational complexity

Abstract

Learning graph convolutional networks (GCNs) is an emerging field which aims at generalizing deep learning to arbitrary non-regular domains. Most of the existing GCNs follow a neighborhood aggregation scheme, where the representation of a node is recursively obtained by aggregating its neighboring node representations using averaging or sorting operations. However, these operations are either ill-posed or weak to be discriminant or increase the number of training parameters and thereby the computational complexity and the risk of overfitting. In this paper, we introduce a novel GCN framework that achieves spatial graph convolution in a reproducing kernel Hilbert space (RKHS). The latter makes it possible to design, via implicit kernel representations, convolutional graph filters in a high dimensional and more discriminating space without increasing the number of training parameters. The particularity of our GCN model also resides in its ability to achieve convolutions without explicitly realigning nodes in the receptive fields of the learned graph filters with those of the input graphs, thereby making convolutions permutation agnostic and well defined. Experiments conducted on the challenging task of skeleton-based action recognition show the superiority of the proposed method against different baselines as well as the related work.