Construct Dynamic Graphs for Hand Gesture Recognition via Spatial-Temporal Attention

Yuxiao Chen (Rutgers University), Long Zhao (Rutgers University), Xi Peng (University of Delaware), Jianbo Yuan (University of Rochester), Dimitris Metaxas (Rutgers University)

Abstract
We propose a Dynamic Graph-Based Spatial-Temporal Attention (DG-STA) method for hand gesture recognition. The key idea is to first construct a fully-connected graph from a hand skeleton, where the node features and edges are then automatically learned via a self-attention mechanism that performs in both spatial and temporal domains. We further propose to leverage the spatial-temporal cues of joint positions to guarantee robust recognition in challenging conditions. In addition, a novel spatial-temporal mask is applied to significantly cut down the computational cost by 99%. We carry out extensive experiments on benchmarks (DHG-14/28 and SHREC'17) and prove the superior performance of our method compared with the state-of-the-art methods. The source code can be found at \url{https://github.com/yuxiaochen1103/DG-STA}.

DOI
10.5244/C.33.48
https://dx.doi.org/10.5244/C.33.48

Files
Paper (PDF)

BibTeX