BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Automatic human behaviour understanding - Tadas Baltrusaitis
DTSTART:20150721T094500Z
DTEND:20150721T104500Z
UID:TALK60154@talks.cam.ac.uk
CONTACT:Alan Blackwell
DESCRIPTION:During social interactions we express ourselves not only throu
 gh words but also through facial expressions\, tone of voice\, gesture and
  body posture. However\, today’s computers are still unable to reliably 
 read and understand such non-verbal signals. Better automatic analysis of 
 human behaviour has numerous applications in the fields of human computer 
 interaction\, education and healthcare. In this talk I will explore the ch
 allenges we still face in automatic human behaviour understanding and the 
 ways to address them. First\, I will talk about capturing the temporal and
  spatial relationships inherent to human behaviour through the use of nove
 l probabilistic models.  Second\, I will discuss the use of multiple types
  of behaviour signals to improve sensing performance. Finally\, I will out
 line the importance of modelling such behaviour in context for further pro
 gression of the field.
LOCATION:Lecture Theatre 2\, Computer Laboratory
END:VEVENT
END:VCALENDAR