Score: 0

Cross-domain EEG-based Emotion Recognition with Contrastive Learning

Published: November 7, 2025 | arXiv ID: 2511.05293v1

By: Rui Yan , Yibo Li , Han Ding and more

Potential Business Impact:

Reads your feelings from brain waves.

Business Areas:
Image Recognition Data and Analytics, Software

Electroencephalogram (EEG)-based emotion recognition is vital for affective computing but faces challenges in feature utilization and cross-domain generalization. This work introduces EmotionCLIP, which reformulates recognition as an EEG-text matching task within the CLIP framework. A tailored backbone, SST-LegoViT, captures spatial, spectral, and temporal features using multi-scale convolution and Transformer modules. Experiments on SEED and SEED-IV datasets show superior cross-subject accuracies of 88.69% and 73.50%, and cross-time accuracies of 88.46% and 77.54%, outperforming existing models. Results demonstrate the effectiveness of multimodal contrastive learning for robust EEG emotion recognition.

Page Count
5 pages

Category
Computer Science:
CV and Pattern Recognition