RealSmileNet: A Deep End-To-End Network for Spontaneous and Posed Smile Recognition
This work addresses the need for automated smile recognition in social interaction analysis, offering a fully automated and faster alternative to feature-engineering methods, though it is incremental as it applies existing deep learning techniques to a specific domain.
The authors tackled the problem of recognizing spontaneous versus posed smiles by proposing RealSmileNet, the first end-to-end deep learning model for this task, which achieved state-of-the-art performance on four datasets.
Smiles play a vital role in the understanding of social interactions within different communities, and reveal the physical state of mind of people in both real and deceptive ways. Several methods have been proposed to recognize spontaneous and posed smiles. All follow a feature-engineering based pipeline requiring costly pre-processing steps such as manual annotation of face landmarks, tracking, segmentation of smile phases, and hand-crafted features. The resulting computation is expensive, and strongly dependent on pre-processing steps. We investigate an end-to-end deep learning model to address these problems, the first end-to-end model for spontaneous and posed smile recognition. Our fully automated model is fast and learns the feature extraction processes by training a series of convolution and ConvLSTM layer from scratch. Our experiments on four datasets demonstrate the robustness and generalization of the proposed model by achieving state-of-the-art performances.