Unsupervised Features for Facial Expression Intensity Estimation over Time
This work addresses the problem of analyzing facial expressions over time for applications in computer vision, but it is incremental as it builds on existing methods for feature extraction.
The paper tackles the challenge of person and expression invariance in facial expression analysis by proposing a feature for estimating expression intensity over time, which outperforms a state-of-the-art method and demonstrates robustness across multiple tasks including temporal alignment and person-specific difference identification.
The diversity of facial shapes and motions among persons is one of the greatest challenges for automatic analysis of facial expressions. In this paper, we propose a feature describing expression intensity over time, while being invariant to person and the type of performed expression. Our feature is a weighted combination of the dynamics of multiple points adapted to the overall expression trajectory. We evaluate our method on several tasks all related to temporal analysis of facial expression. The proposed feature is compared to a state-of-the-art method for expression intensity estimation, which it outperforms. We use our proposed feature to temporally align multiple sequences of recorded 3D facial expressions. Furthermore, we show how our feature can be used to reveal person-specific differences in performances of facial expressions. Additionally, we apply our feature to identify the local changes in face video sequences based on action unit labels. For all the experiments our feature proves to be robust against noise and outliers, making it applicable to a variety of applications for analysis of facial movements.