Automatic Recognition of Facial Displays of Unfelt Emotions
This work addresses the problem of detecting deceptive facial expressions for applications in psychology and human-computer interaction, but it is incremental as it builds on existing emotion recognition methods with a new dataset and feature aggregation.
The authors tackled the problem of automatically recognizing whether facial expressions are genuine or unfelt emotions by introducing the SASE-FE dataset and a method that learns spatio-temporal representations from facial data. They found that distinguishing genuine expressions is easier than unfelt ones, with specific emotion pairs like contempt and disgust being more challenging, and improved state-of-the-art results on CK+ and OULU-CASIA datasets.
Humans modify their facial expressions in order to communicate their internal states and sometimes to mislead observers regarding their true emotional states. Evidence in experimental psychology shows that discriminative facial responses are short and subtle. This suggests that such behavior would be easier to distinguish when captured in high resolution at an increased frame rate. We are proposing SASE-FE, the first dataset of facial expressions that are either congruent or incongruent with underlying emotion states. We show that overall the problem of recognizing whether facial movements are expressions of authentic emotions or not can be successfully addressed by learning spatio-temporal representations of the data. For this purpose, we propose a method that aggregates features along fiducial trajectories in a deeply learnt space. Performance of the proposed model shows that on average it is easier to distinguish among genuine facial expressions of emotion than among unfelt facial expressions of emotion and that certain emotion pairs such as contempt and disgust are more difficult to distinguish than the rest. Furthermore, the proposed methodology improves state of the art results on CK+ and OULU-CASIA datasets for video emotion recognition, and achieves competitive results when classifying facial action units on BP4D datase.