DeepMarkerNet: Leveraging supervision from the Duchenne Marker for spontaneous smile recognition

Mohammad Junayed Hasan, Kazi Rafat, Fuad Rahman, Nabeel Mohammed, Shafin Rahman

Abstract: Highlights•We propose a novel multi-task learning framework for spontaneous smile recognition.•Our framework combines feature-based techniques with deep learning-based approaches.•We attain this by leveraging D-Markers, adding supervision to the deep learning model.•We outperform all SOTA deep learning-based methods on four benchmark datasets.