NeuBCI / semiMVAE

Semi-supervised Multi-view Variational Autoencoder (semiMVAE)

Code for paper “Semi-supervised Bayesian Deep Multi-modal Emotion Recognition”

• Paper: Semi-supervised Bayesian Deep Multi-modal Emotion Recognition
• Authors: Changde Du, Changying Du, Jinpeng Li, Wei-long Zheng, Bao-liang Lu, Huiguang He

Implements the semi-supervised multi-view variational autoencoder (semiMVAE) in TensorFlow (python).

Dependencies

• TensorFlow 1.0
• prettytensor
• numpy
• scipy

Datasets

• SEED: A dataset for emotion recognition using EEG signals
• DEAP: A database for emotion analysis using physiological signals

Usage

• run the file semiMVAE.py directly.

Cite

Please cite our paper if you use this code in your own work:

@article{du2017semi,
  title={Semi-supervised Bayesian Deep Multi-modal Emotion Recognition},
  author={Du, Changde and Du, Changying and Li, Jinpeng and Zheng, Wei-long and Lu, Bao-liang and He, Huiguang},
  journal={arXiv preprint arXiv:1704.07548},
  year={2017}
}

Credits

1. semisupervised_vae
2. Sharing deep generative representation for perceived image reconstruction from human brain activity