Learning Domain- and Class-Disentangled Prototypes for Domain-Generalized EEG Emotion Recognition
A Multi-domain Aggregation Transfer learning framework with domain-class prototypes (MAT) for emotion recognition under completely unseen target domains, which introduces a feature decoupling module to disentangle class-invariant domain features from domain-invariant class features, enabling more robust and interpretab...
Guang-Li Li, Can-Biao Wu, Zhe-Hao Zhou et al.
· IEEE Transactions on Affecti... · 0 citations