Sheng-Hui Peng

Papers

Total Citations

H-Index

About

Sheng-Hui Peng is a computer vision researcher whose work centers on dynamic hand gesture recognition and efficient deep learning architectures for human-computer interaction. His most impactful contribution, "An Efficient Graph Convolution Network for Skeleton-Based Dynamic Hand Gesture Recognition" (2023, 23 citations), addresses a critical challenge in the field: state-of-the-art methods are often over-parameterized, limiting their practical deployment. Peng’s research focuses on designing lean yet powerful graph convolutional networks that maintain high recognition accuracy while significantly reducing computational overhead. This work has direct implications for robotics, augmented reality, and assistive technologies where real-time, resource-efficient gesture understanding is essential. By tackling the trade-off between model complexity and performance, Peng’s contributions help bridge the gap between academic research and real-world applications. His citation record, while still growing, reflects the timely relevance of his work in a rapidly evolving domain. For students and researchers exploring efficient vision architectures or gesture-based interfaces, Peng’s approach offers a compelling blueprint for building models that are both lightweight and effective.