CS395T: Visual Recognition and Search
Spring 2008
Fridays 1-4 pm
Unique # 55910
Instructor: Kristen Grauman
Office hours: by
appointment, CSA 114 (modular building in front of ENS)
Topics Schedule Overview Requirements Books Links Blackboard
Announcements:
Talk
by David Lowe on Monday April 28, 12:00 pm, SEA 4.244, “Object Recognition from
Invariant Local Features”
10-minute project presentations will
be given in class on May 2. Please send
in any slides you will use by May 1.
Overview:
This
is a graduate seminar course in computer vision. We will survey and discuss current computer
vision literature, mainly relating to object recognition and content-based
retrieval for images and videos. The goals
of the course will be to understand current approaches to some important
problems, to actively analyze their strengths and weaknesses, and to identify
interesting open questions and possible directions for future research.
Topics
will include
·
image/video
search and the web
·
recognition
models
·
learning
similarity measures
·
fast indexing
methods
·
data mining with
text and images
·
computational
photography
·
role of context
in recognition
·
unsupervised and
semi-supervised learning from images
A
complete list of topics and papers is here.
Students
will be responsible for writing short paper reviews, participating in
discussions, presenting once or twice throughout the semester, and completing a
research-oriented project (done in pairs).
Our discussions will center around both the relevant research papers as
well as ongoing progress on the class projects.
Prerequisites:
Courses
in computer vision and/or machine learning, probability, linear algebra;
ability to understand and do a high-level analysis of conference papers in this
area. Please talk to me if you are
uncertain if this course will be a good match for your background.
Course requirements:
Students
are expected to do the assigned reading, participate in class discussions,
write one paper review each week, and complete a final project. In addition, everyone will be responsible for
giving two presentations: one that involves doing background research on a
topic (chosen from the provided list), and one that involves an experimental
demo relevant to one of the topics. The
two presentations should be on different topics. After each presentation the class will
provide feedback for the presenter.
Details on each of these elements are provided here.
Grading policy:
Grades
in the class will be determined as follows:
·
20%
Participation (including attendance, in-class discussions, paper reviews,
reviews of student papers)
·
35% Presentation
and demo
·
45% Final
project (including proposal and final paper)
Please
read the UTCS code
of conduct.
Important dates:
March
14: Spring break, no class
April
18: Project paper rough drafts due
May
2: Final project papers due
Books:
There is no required textbook for this course, as we
will get most of our content from the papers we read. However, you may find these books useful
references:
·
Computer vision : a modern
approach, David A. Forsyth and Jean Ponce.
·
Computer vision,
Linda G. Shapiro and George C. Stockman.
·
Introductory
techniques for 3-D computer vision, Emanuele Trucco and Alessandro Verri.
·
Computer vision,
Dana H. Ballard and Christopher M. Brown.
(available online)
·
Multiple view
geometry in computer vision, Richard Hartley and Andrew Zisserman.
·
Pattern classification, Richard O.
Duda, Peter E. Hart, and David G. Stork.
·
Machine learning, Tom M.
Mitchell.
Links:
·
OpenCV (open
source computer vision library)
·
Annotated Computer
Vision Bibliography
·
Weka (Java data mining software)
·
Netlab (Matlab toolbox for data analysis
techniques, written by Ian Nabney and Christopher Bishop)
·
Annotated computer
vision bibliography
·
Computer vision research groups
·
CS
395T Spring 2007 project ideas