CS Events Monthly View

Computer Science Department Colloquium

Learning with Asymmetric Information

 

Download as iCal file

Friday, February 21, 2014, 02:00pm

 

Many computer vision problems have an asymmetric
distribution of information, i.e. less or more information about
a problem is available at training time than at test time. In my
talk I will discuss our recent work on both situations: 1) the
LUPI framework for the case when we have additional data
modalities available for the training data, and 2) a label propagation
approach for the case when an additional similarity measure
is available at test time (both published at ICCV 2013).

Speaker: Christoph H. Lampert

Bio

Christoph Lampert received the PhD degree in mathematics from the Universityof Bonn in 2003. Afterwards, he held postdoctoral positions at the GermanResearch Center for Artificial Intelligence in Kaiserslautern and the Max PlanckInstitute for Biolog

Location : CoRE A(Room 301)

Committee

Dimitris Metaxas

Event Type: Computer Science Department Colloquium

Organization

Institute of Science and Technology, Austria