Invited Keynote Talks


Keynote #1 (Talk Slides)

The Challenges and Opportunities of Mining Billions of Web Images for Search
and Advertising
Dr Wei-Ying Ma
Microsoft Research Asia
http://research.microsoft.com/users/wyma/

Abstract. Although content-based image retrieval has been studied for decades, most commercial search engines still rely on text information to index Web images. This is because of the many fundamental limitations in current content-based image retrieval technologies when applied to Web-scale data and a lack of business incentives to rely on image content for online advertising. In this talk, I will first review what text-based search engines have done to achieve efficient indexing and scalability.  I will then discuss the technical hurdles that exist when we attempt to build systems to analyze and index billions of Web images based on content. I will also present several important
Internet applications that have the potential to take off and make significant impacts if we find ways to overcome existing technical hurdles.

Keynote #2 (Talk Slides)

Visual Information Retrieval: Grand Challenges and Future Directions

Dr. Michael S. Lew
 Leiden Institute of Advanced Computer Science
Leiden University, The Netherlands
http://www.liacs.nl/~mlew/

Abstract. We are at the beginning of the digital Age of Information, a digital Renaissance allowing us to communicate, share, and learn in novel ways and resulting in the creation of new paradigms.  However, having access to all of the knowledge in the world is pointless without a means to search for it. Visual information retrieval is poised to give access to the myriad forms of images and video, comprising knowledge from individuals and cultures to scientific fields and artistic communities.  In this talk I summarize the new paradigms and problems and discuss promising future directions and grand challenges.