Scholarlink

This article is an extended version of the work originally presented at the BIODEVICES 2024 conference, which exclusively focuses on utilizing fEMG as the primary method for action unit recognition (AUR). Within the framework of this study, we employ a proprietary dataset of facial electromyography (fEMG) sensor data, which contains synchronized video modality data with fEMG recordings and output labels corresponding to appropriate AUs, to predict a subset of action units. Abundant feature engineering practice and machine learning experiments are conducted to study fEMG-based AUR.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

EMG-Based Action Unit Recognition: Feature Engineering, Machine Learning, and Real-Time Classification

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Hui Liu,
  • Abhinav Veldanda,
  • Rainer Koschke,
  • Tanja Schultz,
  • Dennis Küster

摘要

This article is an extended version of the work originally presented at the BIODEVICES 2024 conference, which exclusively focuses on utilizing fEMG as the primary method for action unit recognition (AUR). Within the framework of this study, we employ a proprietary dataset of facial electromyography (fEMG) sensor data, which contains synchronized video modality data with fEMG recordings and output labels corresponding to appropriate AUs, to predict a subset of action units. Abundant feature engineering practice and machine learning experiments are conducted to study fEMG-based AUR.