<html><head><style type='text/css'>p { margin: 0; }</style></head><body><div style='font-family: arial,helvetica,sans-serif; font-size: 12pt; color: #000000'><br><div style="color:#000;font-weight:normal;font-style:normal;text-decoration:none;font-family:Helvetica,Arial,sans-serif;font-size:12pt;"><center><font size="+2"><b>What makes Big Visual Data hard?</b></font>
<p><a href="http://www.google.com/url?sa=t&rct=j&q=&esrc=s&frm=1&source=web&cd=1&cad=rja&ved=0CC4QFjAA&url=http%3A%2F%2Fwww.cs.cmu.edu%2F%7Eefros%2F&ei=3OS_UK__LsPO0QHl4oCYCw&usg=AFQjCNEioxKVlyC2wRc-mPV8MfT89GiQ9w&sig2=EMFw28l1AaTHSUskJrvhHA" target="_blank"><font size="+1"><b>Alexei (Alyosha) Efros</b></font></a><br>
Carnegie Mellon University<br>
Princeton CS Colloquium<br>
Monday, Dec 10th<br>
CS 105 (Small Auditorium), 4:30PM<br>
</p>
</center>
<blockquote>There are an estimated 3.5 trillion photographs in the
world, of which 10% have been taken in the past 12 months.
Facebook alone reports 6 billion photo uploads per month. Every
minute, 72 hours of video are uploaded to YouTube. Cisco estimates
that in the next few years, visual data (photos and video) will
account for over 85% of total internet traffic. Yet, we currently
lack effective computational methods for making sense of all this
mass of visual data. Unlike easily indexed content, such as text,
visual content is not routinely searched or mined; it's not even
hyperlinked. Visual data is Internet's "digital dark matter"
[Perona,2010] -- it's just sitting there!
<p>In this talk, I will first discuss some of the unique
challenges that make Big Visual Data difficult compared to other
types of content. In particular, I will argue that the central
problem is the lack a good measure of similarity for visual
data. I will then present some of our recent work that aims to
address this challenge in the context of visual matching, image
retrieval and visual data mining. As an application of the
latter, we used Google Street View data for an entire city in an
attempt to answer that age-old question which has been vexing
poets (and poets-turned-geeks): "What makes Paris look like
Paris?"</p>
</blockquote></div></div></body></html>