SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition

arXiv:2403.09508v1 Announce Type: new
Abstract: Skeleton-based action recognition, which classifies human actions based on the coordinates of joints and their connectivity within skeleton data, is widely utilized in various scenarios. While Graph Convolutional Networks (GCNs) have been proposed for skeleton data represented as graphs, they suffer from limited receptive fields constrained by joint connectivity. To address this limitation, recent advancements have introduced transformer-based methods. However, capturing correlations between all joints in all frames requires substantial memory resources. To alleviate this, …

abstract action recognition arxiv connectivity cs.cv data fields graph graphs human networks recognition temporal transformer type