Automated Affect Detection for Clinical Science and Treatment by Jeffrey Cohn, University of Pittsburgh

ABSTRACT: Facial expression provides a powerful measure of psychological distress and human communication. Advances in analysis of facial expression in clinical settings are hampered by the difficulty of acquiring data in these settings. To address this problem, our research program created well-annotated non-clinical databases that represent challenges likely to emerge in clinical data. We developed approaches to automatic analysis of facial expression and valence that are robust to potential confounds. I present recent work that applies them in multimodal assessment of depression and response to deep brain stimulation (DBS) in patients with previously intractable obsessive-compulsive disorder.

BIO: Jeffrey Cohn, PhD, is a professor of psychology, psychiatry and intelligent systems at the University of Pittsburgh and adjunct professor at the Robotics Institute, Carnegie Mellon University. He leads interdisciplinary and inter-institutional efforts to develop advanced methods of automatic analysis and synthesis of nonverbal behavior and applies them to research in human emotion and psychopathology. He chairs the Steering Committee of the IEEE International Conference on Automatic Face and Gesture Recognition (FG) and has served as General Chair of international conferences on automatic face and gesture recognition, affective computing and multimodal interfaces.