2020/12/28 by Hichem Sahbi, Sahbi, Hichem
Computer Science · Mathematics · #Action recognition #Advanced Graph Neural Networks #Artificial intelligence #Artificial neural network #Class (philosophy) #Computer science #Convolutional neural network #Discrete mathematics #Graph #Hilbert space #Human Pose and Action Recognition #Kernel (algebra) #Mathematics #Multimodal Machine Learning Applications #Overfitting #Pattern recognition (psychology) #Reproducing kernel Hilbert space #Theoretical computer science #cs.CV
paper · pdf · doi:10.48550/arxiv.2012.14186
published in arXiv (Cornell University) (Cornell University) · arXiv admin note: text overlap with arXiv:1912.05864
arxiv created 2020/12/28 · openalex publication_date 2020/12/28 · arxiv updated 2020/12/29 · openalex created_date 2021/01/05 · openalex updated_date 2026/08/05
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.