BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Synthesizing Expressions using Facial Feature Point Tracking: How 
 Emotion is Conveyed - Tadas Baltrusaitis (University of Cambridge)
DTSTART:20101014T131500Z
DTEND:20101014T141500Z
UID:TALK27239@talks.cam.ac.uk
CONTACT:Lech Swirski
DESCRIPTION:Many approaches to the analysis and synthesis of facial expres
 sions rely on automatically tracking landmark points on human faces. Howev
 er\, this approach is usually chosen because of ease of tracking rather th
 an its ability to convey affect. We have conducted an experiment that eval
 uated the perceptual importance of 22 such automatically tracked feature p
 oints in a mental state recognition task. The experiment compared mental s
 tate recognition rates of participants who viewed videos of human actors a
 nd synthetic characters (physical android robot\, virtual avatar\, and vir
 tual stick figure drawings) enacting various facial expressions.\n\nIn thi
 s talk I will present the results of our experiment and the implications t
 hey have for facial feature analysis and synthesis.
LOCATION:Computer Laboratory\, William Gates Building\, Room SS03
END:VEVENT
END:VCALENDAR