Fei-Fei Li : 2010 Plenary Session

 

Wednesday, April 28, 2010
Location: Fisher Conference Center, Arrillaga Alumni Center

"Visual Recognition at the Large-Scale"

Abstract:

By the age of five or six, children have learned to recognize tens and hundreds of thousands of different visual objects and scenes. It is also known that humans can easily tell a detailed story of the visual world in just a glance of a scene, including the detailed objects, scene classes, events and activities. Computer vision today, however, is still far behind. Most of the traditional vision algorithms have only been developed and tested with a few dozen object classes. And the bulk of the research community is still focused on developing algorithms to recognize a small handful of objects. In our lab, we are interested in developing vision algorithms that can see and understand the visual world at the scope (level of details) and scale (large number of visual concepts) that approach humans. In this talk, I'll briefly go over some of our recent research projects towards this goal. In particular, I'll introduce a large-scale dataset effort called ImageNet, where we have built the largest image knowledge ontology available to the research community to date. ImageNet is currently consisted of more than 10 million images across 15,000+ visual categories, all collected from the web and verified by humans. The construction of ImageNet has been a tremendously challenging process, forcing us to dive into relatively unchartered water of crowdsourcing technology. Using ImageNet as a resource, we present here a series of unpublished work in benchmarking existing algorithms for image classification task by using more than 10,000 visual concepts.


Bio:

Prof. Fei-Fei Li's main research interest is in vision, particularly high-level visual recognition. In computer vision, Fei-Fei's interests span from object and natural scene categorization to human activity categorizations in both videos and still images. In human vision, she has studied the interaction of attention and natural scene and object recognition, and decoding the human brain fMRI activities involved in natural scene categorization by using pattern recognition algorithms. Fei-Fei graduated from Princeton University in 1999 with a physics degree. She received her PhD in electrical engineering from the California Institute of Technology in 2005. From 2005 to August 2009, Fei-Fei was an assistant professor in the Electrical and Computer Engineering Department at the University of Illinois Urbana-Champaign and the Computer Science Department at Princeton University, respectively. She is currently an Assistant Professor in the Computer Science Department at Stanford University. Fei-Fei is a recipient of a Microsoft Research New Faculty award and an NSF CAREER award. (Fei-Fei publishes using the name L. Fei-Fei.)