I completed my PhD in 2009 in the Electrical Engineering Department
at Stanford University. I
graduated from Princeton
University in 2002 with a Bachelor's Degree (BSE) in EE, and
finished my Master's Degree (M.S.) at Stanford in 2003. My research
interests are in the areas of image processing, computer
vision, and artificial intelligence. My Ph.D. advisor was Daphne Koller from the Computer Science Department. For awhile at Stanford, I was
supported by the Rambus Stanford Graduate Fellowship.
I'm currently a software engineer at Google. Find out more at my LinkedIn profile.
In my spare time, I develop board games. You can check out (and buy!) my first two: Tower Tycoon and Bloodlines.
In this project we learn probabilistic models for object outlines than
can be used to recognize and detect objects, as well as to answer a
range of "descriptive" queries that go beyond mere categorization.
In this project we attempt to model the relationships
between things (monolithic objects) and stuff (material that spreads
across the image) in order to improve our detection capabilities.
The goal of this project is to integrate many vision models into a single system so that they can improve over the results they would achieve in isolation, through the use of contextual cues flowing between the models.
This site is © Copyright Geremy Heitz 2006, All Rights Reserved.