University of Illinois at Urbana-Champaign Block I logo
university of illinois at urbana-champaign

Department of Computer Science

Artificial Intelligence and Information Systems (AIIS) Seminar

skip to events

calendar tabs

  •  All 
  • Grid
  • Month
  • Week
  • Day
  • (Selected tab) Detail

Event Detail Information

Event Detail Information

Attribute-based classification and the dream of life-long learning for scene understanding

Speaker Christoph Lampert
Date May 3, 2013
Time 2:00 pm  
Sponsor David Forsyth
Views 3295

Abstract

The goal of life-long visual learning is to developing techniques that can continuously and autonomously learn from visual data, potentially for years or decades. During this time the system should build an ever-improving base of generic visual information, and use it as background knowledge and context for solving specific computer vision tasks.

In my talk, I will introduce some challenges that one faces when trying to develop life-long learning computer vision systems and I will discuss some of our recent work on attribute-based and other representations that aim at addressing these challenges.

 

 

 Bio

Christoph Lampert is an assistant professor at IST, Austria. He is very well known for prize winning work on using structured output methods to improve the training and performance of sliding windowmethods.  He is co-author of one of the ground-breaking papers on using visual attributes to describe and recognize objects.  His current interests involve structured learning methods, object detection and recognition, and lifelong visual learning.

link for robots only