Keyframe Selection Via Deep Reinforcement Learning for Skeleton-Based Gesture Recognition

Skeleton-based gesture recognition has attracted extensive attention and has made great progress. However, mainstream methods generally treat all frames as equally im- portant, which may limit performance, especially when dealing with high inter-class variance in gesture. To tackle this issue, we propose an approach that models a Markov decision process to identify keyframes while discarding irrelevant ones. This paper proposes a deep reinforcement learning double-feature double- motion network comprising two main components: a baseline gesture recognition model and a frame selection network. These two components mutually influence each other, resulting in enhanced overall performance. Following the evaluation of the SHREC-17 and F-PHAB datasets, our proposed method demonstrates superior performance.