Event Location: Mauldin Auditorium (NSH 1305)
Bio: Jeffrey Cohn is Professor of Psychology, Associate Professor of Psychiatry, director of the Affect Analysis Group at the University of Pittsburgh, and Adjunct Faculty at the Robotics Institute, Carnegie Mellon University. He earned his PhD in Clinical Psychology from the University of Massachusetts in Amherst and completed his Clinical Internship at the University of Maryland Medical Center.

For the past 25 years, he has investigated the theory and science of emotion, depression, and nonverbal communication. His research has been supported by grants from the National Institute of Mental Health, the National Institute of Child Health and Human Development, the National Science Foundation, the Department of Homeland Security, the Defense Advanced Research Projects Agency, Technical Support Working Group, and the Naval Research Laboratory.

Abstract: Significant efforts have been made in analysis and understanding of naturally occurring behavior. Active appearance models are an especially exciting approach. They may be used both to measure naturally occurring facial behavior and to synthesize photo-realistic real-time avatars with which to experimentally perturb the dynamics of social behavior.

My interdisciplinary group of psychologists and computer scientists uses both of these capabilities. I will present recent studies and the opportunities they offer. Using facial image and acoustic analysis, we achieved the first automated measurements of physical pain and depression severity from expressive behavior; using image synthesis, we seamlessly performed real-time rendering and manipulation of face identity and dynamics. Our findings inform psychology and raise new challenges for computer vision and machine learning.

Challenges include automated detection and synthesis of more subtle facial actions; real-time, multi-modal 3D generic tracking and rendering; computational modeling of subjective states and intentions from multimodal input; and dynamic models of social and affective behavior. Application domains include psychopathology, biomedicine, biometrics, forensics, social development, and its disorders, computer graphics, and entertainment technology.