Action Recognition with Kernel-based Graph Convolutional Networks

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.

arXiv commentarXiv admin note: text overlap with arXiv:1912.05864

References in corpus (20)

• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Inductive Representation Learning on Large Graphs
• Spectral Networks and Locally Connected Networks on Graphs
• Deep Convolutional Networks on Graph-Structured Data
• Simplifying Graph Convolutional Networks
• Variational Graph Auto-Encoders
• An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data
• FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
• Graph Neural Networks with convolutional ARMA filters
• Gated Graph Sequence Neural Networks
• How Powerful are Graph Neural Networks?
• Co-occurrence Feature Learning for Skeleton based Action Recognition using Regularized Deep LSTM Networks
• GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs
• Adaptive Sampling Towards Fast Graph Representation Learning
• Stochastic Training of Graph Convolutional Networks with Variance Reduction
• Pose-conditioned Spatio-Temporal Attention for Human Action Recognition
• Compact Random Feature Maps
• How to Scale Up Kernel Methods to Be As Good As Deep Neural Nets
• Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing
• Stochastic Graphlet Embedding