Through the configuration of facial muscles, facial expressions are assumed to reflect a person’s internal feelings, emotions, motives and needs. It is one of the most heatedly discussed topics in psychology, cognitive neuroscience, and computer science. The general view of emotion recognition may be traced back to Darwin in 1872 when he proposed that human emotions and expressions were innate and universal. In 1992, Ekman proposed six basic emotions: anger, disgust, fear, happiness, sadness, and surprise that people from all cultures could easily read from facial expression.
According to the current knowledge, recognition of facial expression is carried out by a number of interconnected and distributed brain regions. Meanwhile, automatic recognition of facial expression using machine learning technique is also a very popular topic. Some computing methods of automatic recognition are based on the theory of Facial Action Coding system (FACS), which was proposed by Ekman back in 1976. While others do not rely on the theory too much and instead, they input the facial image as a whole and use advanced models such as Deep Neural Network to extract high-level features directly for the facial expression recognition.
The overall goal of this topic is to explore the latest developments in facial expression recognition,aiming to further understand the psychological and cognitive mechanism of how human processing expressions. The scope of this topic includes processing expressions for normal people as well as people with mental disorders, such as depression, schizophrenia, etc. We particularly welcome contributions discussing the computer-based recognition of facial expressions and emotions, the comparison of the similarities and differences between machine recognition and human recognition, and the trend of machine recognition of emotions. The sub-themes include, but are not limited to the following:
• Characteristics of normal people's facial expression recognition
• Recognition of characteristics of patients with depression and other psychiatric disorders
• Features of facial expression recognition using machine learning
• Comparison between machine recognition and human recognition
• Micro expression recognition
• Emotion recognition using multimodal signals
Through the configuration of facial muscles, facial expressions are assumed to reflect a person’s internal feelings, emotions, motives and needs. It is one of the most heatedly discussed topics in psychology, cognitive neuroscience, and computer science. The general view of emotion recognition may be traced back to Darwin in 1872 when he proposed that human emotions and expressions were innate and universal. In 1992, Ekman proposed six basic emotions: anger, disgust, fear, happiness, sadness, and surprise that people from all cultures could easily read from facial expression.
According to the current knowledge, recognition of facial expression is carried out by a number of interconnected and distributed brain regions. Meanwhile, automatic recognition of facial expression using machine learning technique is also a very popular topic. Some computing methods of automatic recognition are based on the theory of Facial Action Coding system (FACS), which was proposed by Ekman back in 1976. While others do not rely on the theory too much and instead, they input the facial image as a whole and use advanced models such as Deep Neural Network to extract high-level features directly for the facial expression recognition.
The overall goal of this topic is to explore the latest developments in facial expression recognition,aiming to further understand the psychological and cognitive mechanism of how human processing expressions. The scope of this topic includes processing expressions for normal people as well as people with mental disorders, such as depression, schizophrenia, etc. We particularly welcome contributions discussing the computer-based recognition of facial expressions and emotions, the comparison of the similarities and differences between machine recognition and human recognition, and the trend of machine recognition of emotions. The sub-themes include, but are not limited to the following:
• Characteristics of normal people's facial expression recognition
• Recognition of characteristics of patients with depression and other psychiatric disorders
• Features of facial expression recognition using machine learning
• Comparison between machine recognition and human recognition
• Micro expression recognition
• Emotion recognition using multimodal signals
