Cross-domain EEG-based Emotion Recognition with Contrastive Learning

Rui Yan, Yibo Li, Han Ding, Fei Wang
11/7/2025
cs.CV

Official code: Departure2021/EmotionCLIP (12 stars, last commit 2025-12-22). 1 more implementation below.

Abstract

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. The code is available at https://github.com/Departure2021/EmotionCLIP.

View on arXivView PDF

Code Implementations(2)

Departure2021/EmotionCLIPOfficial100%
122PythonNov 26, 202510 months ago
MegGitHub/emotion-clipCommunity65%
MIT

A clean PyTorch implementation of EmotionCLIP (arXiv:2511.05293). Features a modular architecture with a custom Trainer class for reproducibility and extendability.

00PythonNov 29, 202510 months agoMIT

Similar Papers

Feature-Based Dual Visual Feature Extraction Model for Compound Multimodal Emotion Recognition

84% match2025

Joint Contrastive Learning with Feature Alignment for Cross-Corpus EEG-based Emotion Recognition

84% match2024

A Cloud-Based Cross-Modal Transformer for Emotion Recognition and Adaptive Human-Computer Interaction

84% match2025

Leveraging Contrastive Learning and Self-Training for Multimodal Emotion Recognition with Limited Labeled Samples

83% match1 repo92024

Enhancing Emotion Recognition in Incomplete Data: A Novel Cross-Modal Alignment, Reconstruction, and Refinement Framework

83% match2024

MultiMAE-DER: Multimodal Masked Autoencoder for Dynamic Emotion Recognition

83% match1 repo192024

Cite this paper

@article{yan2025crossdomain,
  title  = {Cross-domain EEG-based Emotion Recognition with Contrastive Learning},
  author = {Rui Yan and Yibo Li and Han Ding and Fei Wang},
  year   = {2025},
  eprint = {2511.05293},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2511.05293v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2511.05293.svg)](https://codeofpaper.com/paper/2511.05293)

Discussion