Facial expression and action units (AUs) represent two levels of descriptions of the facial behavior. Due to the underlying facial anatomy and the need to form a meaningful coherent expression, they are strongly correlated. This paper proposes to systematically capture their dependencies and incorporate them into a deep learning framework for joint facial expression recognition and action unit detection. Specifically, we first propose a constraint optimization method to encode the generic knowledge on expression-AUs probabilistic dependencies into a Bayesian Network (BN). The BN is then integrated into a deep learning framework as a weak supervision for an AU detection model.

Our proposed approach can be applied to other AUs as well. In Tab.6, LP-SM also considers apex frames on CK+, and The comparison to LP-SM is consistent. In Tab.8, we apply FMPN-FER and DeepEmotion to our pre-processed We will consider a pre-trained VGGFace model in our further work. R2 2.1 The novelty compared to prior work. Facial expression can be a group of AUs.

We adapt the generic knowledge from existing studies that are applicable to different datasets. Generic knowledge is expressed as probabilities. The generic knowledge is categorized into three types: expression-dependent single AU probabilities, expression-dependent joint AU probabilities, and expression-independent joint AU probabilities. 1) For expression-dependent single AU probabilities, two sources are considered. According to FACS, given an expression, AUs can be grouped into primary (P) and secondary (S) categories. The primary AUs are the most expressive AUs with respective to the expression, and the secondary AUs may co-occur with primary AUs providing additional supports for the expression.

Our proposed approach can be applied to other AUs as well. In Tab.6, LP-SM also considers apex frames on CK+, and The comparison to LP-SM is consistent. In Tab.8, we apply FMPN-FER and DeepEmotion to our pre-processed We will consider a pre-trained VGGFace model in our further work. R2 2.1 The novelty compared to prior work. Facial expression can be a group of AUs.

Facial expression and action units (AUs) represent two levels of descriptions of the facial behavior. Due to the underlying facial anatomy and the need to form a meaningful coherent expression, they are strongly correlated. This paper proposes to systematically capture their dependencies and incorporate them into a deep learning framework for joint facial expression recognition and action unit detection. Specifically, we first propose a constraint optimization method to encode the generic knowledge on expression-AUs probabilistic dependencies into a Bayesian Network (BN). The BN is then integrated into a deep learning framework as a weak supervision for an AU detection model.

Expert system can process large amounts of known information and apply reasoning capabilities to provide conclusions. An expert system is a system that employs human knowledge captured in an automated system to solve problems that typically require human expertise. In this paper we propose the design and development of a medical knowledge based system (MKBS) for disease diagnosis from symptoms. It provides rich features for searching properties like symptoms, treatments, hierarchical clusters of particular diseases. The system supports a knowledge construction module and an inference engine module. The knowledge construction was built on a concept of rules, which was represented in a tree structure, and properties of a particular disease were stored as a semantic net.