Quantified Facial Expressiveness for Affective Behavior Analytics
This work addresses the need for scalable affective behavior analytics by providing a method to measure facial expressiveness, though it appears incremental as it builds on existing multimodal features without introducing a new paradigm.
The authors tackled the problem of quantifying facial expressiveness at the video frame-level, which is underexplored compared to discrete expression analysis, by proposing an algorithm that uses multimodal facial features to compute a bounded, continuous expressiveness score, with results showing effectiveness in capturing temporal changes and subjective differences on benchmark datasets.
The quantified measurement of facial expressiveness is crucial to analyze human affective behavior at scale. Unfortunately, methods for expressiveness quantification at the video frame-level are largely unexplored, unlike the study of discrete expression. In this work, we propose an algorithm that quantifies facial expressiveness using a bounded, continuous expressiveness score using multimodal facial features, such as action units (AUs), landmarks, head pose, and gaze. The proposed algorithm more heavily weights AUs with high intensities and large temporal changes. The proposed algorithm can compute the expressiveness in terms of discrete expression, and can be used to perform tasks including facial behavior tracking and subjectivity quantification in context. Our results on benchmark datasets show the proposed algorithm is effective in terms of capturing temporal changes and expressiveness, measuring subjective differences in context, and extracting useful insight.