[PAST EVENT] Computer Science/CSUMS Lecture: David Crandall

April 14, 2011
McGlothlin-Street Hall, Room 020
251 Jamestown Rd
Williamsburg, VA 23185Map this location
The rapid rise of social photo-sharing websites has created immense collections of photographs online, with {{http://www.flickr.com,Flickr}} and {{http://www.facebook.com,Facebook}} alone now hosting over 50 billion images. The sheer size of these sites raises both challenges and opportunities. A major challenge is how to organize large photo collections effectively since modern photo-sharing sites rely on relatively primitive technology like keyword tags (causing untagged or poorly-tagged photographs to be essentially impossible to find). An opportunity is that these sites contain a vast amount of visual information about the world and its people, contributed by millions of photographers worldwide, that could be a new data source for scientists in a variety of disciplines. In this talk I'll describe some of our recent work both in organizing large-scale photo collections and in using these collections to mine for information about the world and human behavior. For example, I'll show how we use data mining techniques to automatically produce annotated maps of the world using nearly 100 million photographs downloaded from Flickr, and how we use computer vision techniques to efficiently reconstruct 3-d models of popular landmarks. I'll also show how combining computer vision, data mining, and machine learning lets us extract information from large photo collections for use in interdisciplinary studies with fields as diverse as sociology, economics, and ecology.


David Crandall is an assistant professor at Indiana University in Bloomington. He received the Ph.D. in computer science from Cornell University in 2008 and M.S. and B.S. degrees in computer science and engineering from the Pennsylvania State University, University Park, in 2001. He was a Postdoctoral Research Associate at Cornell from 2008-2010, and a Senior Research Scientist with Eastman Kodak Company in Rochester, NY from 2001-2003. His main research interests are computer vision and data mining, with a focus on visual object recognition, image understanding, machine learning, and mining and modeling of complex networks.

[[w|vjtorc,Virginia Torczon]]