Transfer Learning for Action Unit Recognition
This work addresses facial expression analysis for applications like human-computer interaction, but it is incremental as it builds on existing transfer learning and ensemble methods.
The paper tackles facial action unit recognition by comparing classifier ensembles using transfer learning from pre-trained CNNs like VGG-Face and ResNet, achieving the best results with an ensemble of VGG-Net variants and ResNet.
This paper presents a classifier ensemble for Facial Expression Recognition (FER) based on models derived from transfer learning. The main experimentation work is conducted for facial action unit detection using feature extraction and fine-tuning convolutional neural networks (CNNs). Several classifiers for extracted CNN codes such as Linear Discriminant Analysis (LDA), Support Vector Machines (SVMs) and Long Short-Term Memory (LSTM) are compared and evaluated. Multi-model ensembles are also used to further improve the performance. We have found that VGG-Face and ResNet are the relatively optimal pre-trained models for action unit recognition using feature extraction and the ensemble of VGG-Net variants and ResNet achieves the best result.