Deep Covariance Descriptors for Facial Expression Recognition
This work addresses facial expression recognition, a domain-specific problem in computer vision, with an incremental improvement over existing methods.
The paper tackled facial expression recognition by encoding deep convolutional neural network features with covariance matrices and classifying them on a Symmetric Positive Definite manifold using a Gaussian kernel. It achieved state-of-the-art performance on the Oulu-CASIA and SFEW datasets.
In this paper, covariance matrices are exploited to encode the deep convolutional neural networks (DCNN) features for facial expression recognition. The space geometry of the covariance matrices is that of Symmetric Positive Definite (SPD) matrices. By performing the classification of the facial expressions using Gaussian kernel on SPD manifold, we show that the covariance descriptors computed on DCNN features are more efficient than the standard classification with fully connected layers and softmax. By implementing our approach using the VGG-face and ExpNet architectures with extensive experiments on the Oulu-CASIA and SFEW datasets, we show that the proposed approach achieves performance at the state of the art for facial expression recognition.