<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>
<head>
<meta content="text/html;charset=UTF-8" http-equiv="Content-Type">
</head>
<body bgcolor="#ffffff" text="#000000">
Dobry den,<br>
<br>
rad bych vas pozval na zitrejsi seminar:<br>
<br>
<strong>Josef Sivic</strong>, Department of Engineering Science,
University of Oxford: <i><u>Efficient visual search of images and
videos</u></i>
<br>
<br>
<i>Abstract:</i><br>
The objective of this work is to search videos and image collections
based on their visual content. Despite the recent success of text
based search (e.g. Google), visual search in unannotated image and
video collections remains a challenging problem. The imaged appearance
of a particular object can change significantly due to changing camera
viewpoint, illumination, and partial occlusion by other
objects. Furthermore, there is additional
variation when searching for visual object classes, such as cars,
buildings or people, rather than a particular object, e.g. the Eiffel
Tower.
<br>
Inspired by the success of textual search, we have developed a novel
object representation where an image is described as a collection of
visual 'nouns', as analogues of words. These descriptors are built
with a controlled degree of invariance to certain appearance
transformations. This new representation allows us to employ
efficient search methods and probabilistic models from statistical
text analysis.
<br>
In the first part of the talk, I will show rapid retrieval of
particular
objects and people in videos. In the second part of the talk
I will show how probabilistic topic discovery methods from statistical
text analysis can be used to learn models of visual object classes
from an unlabelled collection of images. The learnt models
are then applied to object class retrieval in image databases
and films.
<br>
Joint work with Andrew Zisserman, Alexei Efros, Bryan Russell,
and William Freeman.<br>
<br>
<pre class="moz-signature" cols="72">--
Tomas Bures
Distributed Systems Research Group
Department of Software Engineering
Faculty of Mathematics and Physics
Charles University, Czech Republic
<a class="moz-txt-link-freetext" href="http://nenya.ms.mff.cuni.cz/~bures">http://nenya.ms.mff.cuni.cz/~bures</a>
</pre>
</body>
</html>