ICE-GAN: Identity-aware and Capsule-Enhanced GAN with
Graph-based Reasoning for Micro-Expression Recognition and Synthesis

  • 1University of Sydney
  • 2University of New South Wales

Overview

overview

Micro-expressions are reflections of people’s true feelings and motives, which attract an increasing number of researchers into the study of automatic facial micro-expression recognition. The short detection window, the subtle facial muscle movements, and the limited training samples make micro-expression recognition challenging. To this end, we propose a novel Identity-aware and Capsule-Enhanced Generative Adversarial Network with graph-based reasoning (ICE-GAN), introducing micro-expression synthesis as an auxiliary task to assist recognition. The generator produces synthetic faces with controllable micro-expressions and identity-aware features, whose long-ranged dependencies are captured through the graph reasoning module (GRM), and the discriminator detects the image authenticity and expression classes. Our ICE-GAN was evaluated on Micro-Expression Grand Challenge 2019 (MEGC2019) with a significant improvement (12.9%) over the winner and surpassed other state-of-the-art methods.

Evaluation Benchmark

benchmark

BibTeX

If you find our project useful in your research, please cite:
@InProceedings{yu2020ice,
    title     = {ICE-GAN: Identity-aware and Capsule-Enhanced GAN with Graph-based Reasoning for Micro-Expression Recognition and Synthesis},
    author    = {Yu, Jianhui and Zhang, Chaoyi and Song, Yang and Cai, Weidong},
    booktitle = {International Joint Conference on Neural Networks (IJCNN)},
    year      = {2021}
}

Acknowledgments

The website template was borrowed from Zhenqin Li's project.