[Ml-stat-talks] W 12/15 at 1:30PM, Fei-Fei Li (Stanford)

David Blei blei at CS.Princeton.EDU
Mon Dec 13 17:25:12 EST 2010


hi all

fei-fei li returns to princeton!  join us on W 12/15 at 1:30PM.  the
abstract looks fascinating, and fei-fei is a great speaker.

best
dave


    Speaker: Fei-Fei Li (Stanford University)
 Title: Visual recognition: handling hidden structure, high dimensionality
and large-scale data
Date: Wednesday, December 15
Location: Sherrerd 213 (Statistics Lab)

Understanding the meaning and structure of images is a central topic in
computer vision. In this talk, I present a number of recent projects from
our lab on tackling the problems of scene understanding, object recognition
and human-object interactions. Each of these visual recognition tasks
highlights an aspect of the challenges in vision: inferring hidden
structure, handling high dimensionality, and classifying tens of thousands
of objects in a data ontology of tens of millions of samples. We show how we
use structural learning, non-parametric Bayes, sparsification and efficient
metric learning methods in both generative and discriminative frameworks to
approach these problems. I will especially discuss a new image
representation called the "Object Bank", useful for a number of high-level
visual recognition tasks.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.cs.princeton.edu/pipermail/ml-stat-talks/attachments/20101213/1c71fd33/attachment.html>


More information about the Ml-stat-talks mailing list