#machine learning
Jul 2026
Masked Generative-Contrastive Representation Learning for Cross-Dataset EEG-Based Emotion Recognition
MGCRL is a novel SSL framework specifically designed for EEG-based emotion recognition that integrates generative and contrastive learning to achieve both fine-grained and global discriminative representations for cross-dataset generalization.
Huqin Weng, Jiayang Huang, Yimin Wen et al.
· Neurocomputing · 0 citations