@inproceedings{Buechner23:ACIVS,
    type = {inproceedings},
    key = {Buechner23:ACIVS},
    title = {Improved Obstructed Facial Feature Reconstruction for Emotion Recognition with Minimal Change CycleGANs},
    author = {Tim Büchner and Orlando Guntinas-Lichius and Joachim Denzler},
    booktitle = {Advanced Concepts for Intelligent Vision Systems (Acivs)},
    editor = {J. Blanc-Talon, D. Popescu, W. Philips, and P. Scheunders},
    year = {2023},
    pages = {262-274},
    organization = {SpringerNature},
    publisher = {SpringerNature},
    note = {Best Paper Award},
    abstract = {Comprehending facial expressions is essential for human interaction and closely linked to facial muscle understanding. Typically, muscle activation measurement involves electromyography (EMG) surface electrodes on the face. Consequently, facial regions are obscured by electrodes, posing challenges for computer vision algorithms to assess facial expressions. Conventional methods are unable to assess facial expressions with occluded features due to lack of training on such data. We demonstrate that a CycleGAN-based approach can restore occluded facial features without fine-tuning models and algorithms. By introducing the minimal change regularization term to the optimization problem for CycleGANs, we enhanced existing methods, reducing hallucinated facial features. We reached a correct emotion classification rate up to 90\% for individual subjects. Furthermore, we overcome individual model limitations by training a single model for multiple individuals. This allows for the integration of EMG-based expression recognition with existing computer vision algorithms, enriching facial understanding and potentially improving the connection between muscle activity and expressions.},
    groups = {facialpalsy},
    doi = {10.1007/978-3-031-45382-3_22},
    url = {https://link.springer.com/chapter/10.1007/978-3-031-45382-3_22},
    isbn = {978-3-031-45382-3},
    issn = {0302-9743},
    langid = {english},
}