The Fourth Workshop on Face and Gesture Analysis for Health Informatics

About Face and Gesture Analysis for Health Informatics (FGAHI)

Within the past 10 years great strides have been made in the computer vision and machine learning community, as well as sensing technology for the modeling, analysis and synthesis of human verbal and nonverbal behavior (e.g., audio, video, text, thermal, physiological, etc.) for healthcare related applications. For instance, on-board smartphone sensors and wearable devices that track user activity, sleeping and eating habits, blood pressure, heart rate, skin temperature, and movement. However, compared to the advances in sensing technology, the current advances in computer vision and machine learning for verbal and nonverbal analysis (e.g., facial expression and body movement) has not yet achieved the goal of moving from the laboratory to the real-world healthcare context (e.g., medical setting). Recent advances in computer vision and machine learning for automatic analysis and modeling of human behavior could be used to reliably and objectively measure the physical, mental and social wellness beyond the classical definition of health assessment. 

To improve clinical assessment and guide treatment, automatic, reliable, and valid multimodal human behavior assessment in clinical context is needed. There is an ever-growing research interests of the computer vision and machine learning community in modeling human facial and gestural behavior for clinical applications. One main challenge to achieve this goal is the lack of available archives of behavioral observations of individuals that have clinically relevant conditions (e.g., pain, depression, autism spectrum). Well-labeled recordings of clinically relevant conditions are necessary to train classifiers. Interdisciplinary efforts to address this necessity are ongoing. 

The workshop aims to gather researchers working in different domains (from low-level sensing for face, head, and body detection to high-level modeling of complex social and clinically relevant behavior) to discuss the strengths and major challenges in using computer vision and machine learning of automatic modeling of face and gesture for clinical research and healthcare applications. We invite scientists working in related areas of computer vision and machine learning for face and gesture detection, affective computing, multimodal human behavior modeling, and cognitive behavior to share their expertise and achievements in the emerging field of computer vision and machine learning based face and gesture analysis for health informatics.