BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Facial landmark detection in unconstrained environments - Tadas
DTSTART:20131121T111500Z
DTEND:20131121T121500Z
UID:TALK48523@talks.cam.ac.uk
CONTACT:Jingjing Shen
DESCRIPTION:Automatic facial landmark detection is a longstanding problem 
 in computer vision. Facial feature detection algorithms have seen great pr
 ogress over the recent years. However\, they still struggle in poor lighti
 ng conditions and in the presence of extreme pose or occlusions. I will pr
 esent the Constrained Local Neural Field model for facial landmark detecti
 on that deals with some of these problems and demonstrates state of the ar
 t performance on a number of datasets. This is a practice talk for Interna
 tional Conference on Computer Vision\, 300 faces in-the-wild challenge.
LOCATION:Rainbow Seminar Room (SS03)\, Computer Laboratory
END:VEVENT
END:VCALENDAR