<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40">
<head>
<meta http-equiv=Content-Type content="text/html; charset=utf-8">
<meta name=Generator content="Microsoft Word 12 (filtered medium)">
<style>
<!--
/* Font Definitions */
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
margin-bottom:.0001pt;
font-size:12.0pt;
font-family:"Times New Roman","serif";}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:blue;
text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
{mso-style-priority:99;
color:purple;
text-decoration:underline;}
span.apple-style-span
{mso-style-name:apple-style-span;}
span.EmailStyle18
{mso-style-type:personal-reply;
font-family:"Arial","sans-serif";
color:blue;
font-weight:normal;
font-style:normal;
text-decoration:none none;}
.MsoChpDefault
{mso-style-type:export-only;}
@page Section1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;}
div.Section1
{page:Section1;}
-->
</style>
<!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]-->
</head>
<body lang=EN-US link=blue vlink=purple>
<div class=Section1>
<p class=MsoNormal><span style='font-size:9.0pt;font-family:"Arial","sans-serif";
color:blue'>Min Sun will present his research seminar/general exam on Wednesday
April 22 at 3:30PM in Room 402. <o:p></o:p></span></p>
<p class=MsoNormal><span style='font-size:9.0pt;font-family:"Arial","sans-serif";
color:blue'>The members of his committee are; Fei-Fei Li (advisor), David
Blei, Adam Finkelstein. Everyone is <o:p></o:p></span></p>
<p class=MsoNormal><span style='font-size:9.0pt;font-family:"Arial","sans-serif";
color:blue'>invited to attend his talk and those faculty wishing to remain for
the oral exam following are welcome <o:p></o:p></span></p>
<p class=MsoNormal><span style='font-size:9.0pt;font-family:"Arial","sans-serif";
color:blue'>to do so. His abstract and reading list follow below.<o:p></o:p></span></p>
<p class=MsoNormal><span style='font-size:9.0pt;font-family:"Arial","sans-serif";
color:blue'>-------------------------------------------------<o:p></o:p></span></p>
<p class=MsoNormal><span style='font-size:9.0pt;font-family:"Arial","sans-serif";
color:blue'><o:p> </o:p></span></p>
<p class=MsoNormal><span class=apple-style-span>We propose a novel
probabilistic framework for learning visual models of 3D object categories
by combining appearance information and geometric constraints. Objects
are represented as a coherent ensemble of parts that are consistent under
3D viewpoint transformations. Each part is a collection of salient image
features. A generative framework is used for learning a model that captures the
relative position of parts within each of the discretized
viewpoints. Contrary to most of the existing mixture of viewpoints models,
our model establishes explicit correspondences of parts across different
viewpoints of the object class. Given a new image, detection and
classification are achieved by determining the position and viewpoint of the
model that maximize recognition scores of the candidate objects. Our approach
is among the first to propose a generative probabilistic framework for 3D object
categorization. We test our algorithm on the detection task and the
viewpoint classification task by using “car” category from both the Savarese et
al. 2007 and PASCAL VOC 2006 datasets. We show promising results in both
the detection and viewpoint classification tasks on these two challenging
datasets.</span><o:p></o:p></p>
<p class=MsoNormal><span style='font-size:9.0pt;font-family:"Arial","sans-serif";
color:blue'><o:p> </o:p></span></p>
<div>
<p class=MsoNormal>=======<o:p></o:p></p>
</div>
<div>
<p class=MsoNormal><span class=apple-style-span>Reading list:</span><o:p></o:p></p>
</div>
<p class=MsoNormal><span class=apple-style-span>• Textbooks</span><br>
<span class=apple-style-span>[1] C. M. Bishop. Pattern Recognition and Machine</span><br>
<span class=apple-style-span>Learning (Information Science and Statistics).</span><br>
<span class=apple-style-span>Springer, August 2006. Chapter 1, 2, 8, and 10.</span><br>
<span class=apple-style-span>[2] D. A. Forsyth and J. Ponce. Computer Vision: A
Modern</span><br>
<span class=apple-style-span>Approach. Prentice Hall, August 2002.</span><br>
<span class=apple-style-span>• Papers</span><br>
<span class=apple-style-span>[1] D. M. Blei. Variational methods for the
dirichlet process.</span><br>
<span class=apple-style-span>In In Proceedings of the 21st International
Conference</span><br>
<span class=apple-style-span>on Machine Learning, 2004.</span><br>
<span class=apple-style-span>[2] P. F. Felzenszwalb and D. P. Huttenlocher.
Pictorial</span><br>
<span class=apple-style-span>structures for object recognition. IJCV, 61:2005,
2005.</span><br>
<span class=apple-style-span>[3] D. Hoeim, C. Rother, and J. Winn. 3d layoutcrf
for</span><br>
<span class=apple-style-span>multi-view object class recognition and segmentation.</span><br>
<span class=apple-style-span>2007. In Proc. In IEEE Conference on Computer
Vision</span><br>
<span class=apple-style-span>and Pattern Recognition.</span><br>
<span class=apple-style-span>[4] A. Kushal, C. Schmid, , and J. Ponce. Flexible
object</span><br>
<span class=apple-style-span>models for category-level 3d object recognition.</span><br>
<span class=apple-style-span>2007. Flexible object models for category-level 3d
object</span><br>
<span class=apple-style-span>recognition. In Proc. In IEEE Conf. on Comp. Vis.</span><br>
<span class=apple-style-span>and Patt. Recogn.</span><br>
<span class=apple-style-span>[5] B. Leibe, A. Leonardis, and B. Schiele.
Combined object</span><br>
<span class=apple-style-span>categorization and segmentation with an implicit</span><br>
<span class=apple-style-span>shape model. In In ECCV workshop on statistical</span><br>
<span class=apple-style-span>learning in computer vision, pages 17–32, 2004.</span><br>
<span class=apple-style-span>[6] J. Liebelt, C. Schmid, and K. Schertler.
Viewpointindependent</span><br>
<span class=apple-style-span>object class detection using 3d feature</span><br>
<span class=apple-style-span>maps. Computer Vision and Pattern Recognition,
2008.</span><br>
<span class=apple-style-span>CVPR 2008. IEEE Conference on, pages 1–8, June</span><br>
<span class=apple-style-span>2008.</span><br>
<span class=apple-style-span>[7] S. Savarese and L. Fei-Fei. 3d generic object
categorization,</span><br>
<span class=apple-style-span>localization and pose estimation. 2007. IEEE</span><br>
<span class=apple-style-span>Intern. Conf. in Computer Vision (ICCV).</span><br>
<span class=apple-style-span>[8] E. B. Sudderth, A. Torralba, W. T. Freeman,
and A. S.</span><br>
<span class=apple-style-span>Willsky. Describing visual scenes using
transformed</span><br>
<span class=apple-style-span>dirichlet processes. In In NIPS, pages 1297–1304.
MIT</span><br>
<span class=apple-style-span>Press, 2005.</span><br>
<span class=apple-style-span>[9] A. Thomas, V. Ferrari, B. Leibe, T.
Tuytelaars,</span><br>
<span class=apple-style-span>B. Schiele, and L. V. Goo. Towards multi-view
object</span><br>
<span class=apple-style-span>class detection. In Proc. In IEEE Conference on
Computer</span><br>
<span class=apple-style-span>Vision and Pattern Recognition, volume 2, pages</span><br>
<span class=apple-style-span>1589-1596.</span><br>
<span class=apple-style-span>[10] P. Yan, D. Khan, and M. Shah. 3d model based
object</span><br>
<span class=apple-style-span>class detection in an arbitrary view. ICCV, 2007.</span><o:p></o:p></p>
</div>
</body>
</html>