Bi-branch Vision Transformer Network for EEG Emotion Recognition

Electroencephalogram (EEG) signals have emerged as an important tool for emotion research due to their objective reflection of real emotional states. Deep learning-based EEG classification algorithms made preliminary progress, but existing models struggle with capturing long-range dependence and integrating temporal, frequency, spatial domain features limit ability. To address these challenges, this study proposes a Bi-branch Vision Transformer-based recognition model, Bi-ViTNet, that integrates spatial-temporal spatial-frequency feature representations. Specifically, Bi-ViTNet is composed extraction branch branch, which can fuse spatial-frequency-temporal in unified framework. Each Linear Embedding Transformer Encoder, used extract features. Finally, fusion are performed by the Fusion Classification layer. Experiments on SEED SEED-IV datasets demonstrate outperforms state-of-the-art baselines.