BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Dictionaries\, Manifolds and Domain Adaptation for Computer Vision
  and Pattern Recognition
DTSTART:20140605T143000
DTEND:20140605T153000
DTSTAMP:20260928T210202Z
UID:308cb5ee7bf03c8d85cf3da42d091e0733bd6f5f43c54eb796fa2d13
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Rama Chellappa\, University of Maryland\nAbstract: Featu
 re extraction or representation of patterns and adaptation of classifiers 
 designed using training data to be effective on testing data are two funda
 mental problems in computer vision and pattern recognition. In this talk\,
  I will discuss recent solutions to these problems based on theories of di
 ctionary learning\, manifold representations and domain adaptation. Specif
 ically\, I will discuss methods for representing images and videos using l
 inear and non-linear dictionaries as well as special manifolds. I will the
 n discuss methods for adapting the dictionaries and manifolds for addressi
 ng shifts in data distributions due to changes in pose\, illumination and 
 resolution with applications in face\, object and event recognition.\nBio:
  Prof. Rama Chellappa is a Minta Martin Professor of Engineering and the C
 hair of the ECE department at University of Maryland.  Prof. Chellappa re
 ceived the K.S. Fu Prize from the International Association of Pattern Rec
 ognition (IAPR). He is a recipient of the Society\, Technical Achievement 
 and Meritorious Service Awards from the IEEE Signal Processing Society. He
  also received the Technical Achievement and Meritorious Service Awards fr
 om the IEEE Computer Society. At UMD\, he received college and university 
 level recognitions for research\, teaching\, innovation and mentoring of u
 ndergraduate students. In 2010\, he was recognized as an Outstanding  ECE
  by Purdue University. Prof. Chellappa served as the Editor-in-Chief of PA
 MI. He is a Golden Core Member of the IEEE Computer Society\, served as a 
 Distinguished Lecturer of the IEEE Signal Processing Society and as the Pr
 esident of IEEE Biometrics Council. He is a Fellow of IEEE\, IAPR\, OSA\, 
 AAAS and ACM and holds four patents
LOCATION:SV1717A http://plan.epfl.ch/?lang=fr&room=SV1717A
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR