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

TL;DR

This paper introduces DG-STA, a dynamic graph-based method utilizing spatial-temporal attention for hand gesture recognition, achieving high accuracy and efficiency by automatically learning graph features and reducing computational costs.

Contribution

The paper presents a novel dynamic graph construction with self-attention for hand gesture recognition, significantly reducing computational cost and improving robustness in challenging conditions.

Findings

Outperforms state-of-the-art on DHG-14/28 and SHREC'17 datasets.

Reduces computational cost by 99% with a new spatial-temporal mask.

Demonstrates robustness in challenging recognition scenarios.

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 https://github.com/yuxiaochen1103/DG-STA.