BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//NextToU//EN
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:20734137-bd1d-4c55-8891-7aaf5073a252@nexttoyou
DTSTAMP:20261105T161152Z
DTSTART:20261106T220000Z
DTEND:20261106T233000Z
SUMMARY:Leveraging AI to Measure and Model Social Behavior
LOCATION:Kelley Engineering Center 1001\, 2461 SW Campus Way\, Corvallis\,
  OR 97331
DESCRIPTION:Speaker: James M. Rehg\, Professor\, University of Illinois Ur
 bana-Champaign\n\nDate: Nov 6\n\nTime: 2:00-3:00 PM\n\nQ&A: 3:00-3:30 PM\
 n\nLocation: KEC 1001\n\nZoom\n\nTitle: Leveraging AI to Measure and Mode
 l Social Behavior\n\nAbstract:\n\nBeginning in infancy\, individuals acqu
 ire the social and communication skills that are vital for a healthy and 
 productive life. Children with autism face great challenges in acquiring 
 these skills\, resulting in substantial lifetime risks. The diagnosis\, t
 reatment\, and study of autism depends fundamentally on the analysis of c
 hild behavior. Standard methods for behavioral observation and coding are
  the backbone of research studies but are inherently coarse-grained and n
 ot easily scalable. In this talk I will present our research in developin
 g AI models and computer vision technology to automate the measurement of
  social behavior from video. Our goal is to unlock the rich behavioral in
 formation that is present in video and make it available for large-scale 
 data-driven modeling\, phenotyping\, and assessment. I will present sever
 al recent findings which demonstrate the feasibility of this approach. Th
 e first is a method for detecting eye contact during naturalistic face-to
 -face interactions\, which has been shown to achieve human-level accuracy
 \, and it's extension to more general social gaze behaviors. I will also 
 describe progress in developing longitudinal models of language developme
 nt in ASD with the goal of predicting the risk for minimally verbal outco
 mes.\n\nhttp://next-to-u.app/events/20734137-bd1d-4c55-8891-7aaf5073a252
URL:http://next-to-u.app/events/20734137-bd1d-4c55-8891-7aaf5073a252
END:VEVENT
END:VCALENDAR
