AI RESEARCH
EMGFlow: Robust and Efficient Surface Electromyography Synthesis via Flow Matching
arXiv CS.LG
•
ArXi:2604.13685v1 Announce Type: cross Deep learning-based surface electromyography (sEMG) gesture recognition is frequently bottlenecked by data scarcity and limited subject diversity. While synthetic data generation via Generative Adversarial Networks (GANs) and diffusion models has emerged as a promising augmentation strategy, these approaches often face challenges regarding