An Improved Graph Pooling Network for Skeleton-Based Action Recognition

arXiv:2404.16359v1 Announce Type: new
Abstract: Pooling is a crucial operation in computer vision, yet the unique structure of skeletons hinders the application of existing pooling strategies to skeleton graph modelling. In this paper, we propose an Improved Graph Pooling Network, referred to as IGPN. The main innovations include: Our method incorporates a region-awareness pooling strategy based on structural partitioning. The correlation matrix of the original feature is used to adaptively adjust the weight of information in different regions of the …

abstract action recognition application arxiv computer computer vision cs.cv graph innovations modelling network paper pooling recognition strategies type unique vision