Vincent Cheung
Office Office: (416) 946-8810
University of Toronto, Bahen Centre Room 4159 Home: (416) 944-2535
40 St. George
St., Toronto, ON, M5S 3G4, Canada Fax: (416) 978-4425
vincent@psi.toronto.edu
Mailing Address www.psi.toronto.edu/~vincent
2410-666
Spadina Ave., Toronto, ON, M5S 2H8, Canada
Education
Ph.D. Computer Engineering Sept. 2004 - Present
University of Toronto, Toronto, Ontario
Thesis: Probabilistic Graphical Models for Computer Vision and Computational Biology
Advisor: Brendan J. Frey
M.Sc. Computer Engineering Sept. 2003 - Aug. 2004
University of Toronto, Toronto, Ontario
Transferred
to the Ph.D. program in Sept. 2004
B.Sc. Computer Engineering (Honours with Distinction) May 2003
University of Manitoba, Winnipeg, Manitoba
GPA: 4.49/4.50
Governor General’s Silver Medal for the highest undergraduate academic standing
Thesis: Signal Classification through
Multifractal Analysis and Neural Networks
Advisor: Witold Kinsner
Honours and Awards
Title Amount Year
IEEE CVPR Best Paper Honourable Mention Award USD $1,000 2005
NSERC Canada Graduate Scholarship – Doctoral CAD $105,000 2004 - 2007
NSERC Canada Graduate Scholarship – Master’s CAD $17,500 2003 - 2004
Governor General’s Silver (Undergraduate) Medal 2003
University Gold Medal in Engineering 2003
Faculty of Engineering Medal in Computer Engineering 2003
U of
M Undergraduate Thesis Award in Elec. & Comp. Eng. 2003
U of
M Students' Teacher Recognition Award 2003
NSERC Undergraduate Student Research Award CAD $4,500 2002
32 Undergraduate Scholarships CAD $25,575 1999 - 2003
Dean’s Honour List 1999 - 2003
Governor General’s Bronze (High School) Medal 1999
Research Interests
·
Engineering principled machine
learning solutions to a variety of problems, including those in computer vision
and computational biology; solutions that both solve the problem at hand, yet
are general enough to apply to completely different datasets or even other
domains.
·
Developing and using distributed
computing systems in conjunction with machine learning algorithms.
Research Experience
Computer
Vision and Machine Learning Research Assistant 2003
- Present
University
of Toronto, Dept. Elec. & Comp. Eng., Toronto,
Ontario
Advisor: Brendan J. Frey
·
Researched the modelling of a video
sequence by a smaller sequence, called its “video epitome”, with applications
in object removal, video inpainting, frame interpolation, and video
super-resolution. Implementations
were done in Matlab, Java, and C#.
·
Explored some of the open problems in
the epitome framework including determining the size of the epitome and its
computational issues.
·
A distributed computing system was
developed in Java, in which clients could be run on any machine that supports
the Java JVM, including Windows, Mac, and Linux desktops as well as Linux
clusters. This distributed
representation resulted in a considerable speed improvement in both computing
and utilizing video epitomes.
Computational
Biology Research Assistant 2005
- Present
University
of Toronto, Dept. Elec. & Comp. Eng., Toronto,
Ontario
Advisor: Brendan J. Frey
·
Collaborated with Charlie Boone (U.
Toronto), Jack Greenblatt (U. Toronto), and Nevan Krogan (UCSF) to analyze
their yeast gene interaction and cell biology datasets.
·
Invented the “factorgram”, which is a
tool for visualizing multi-way associations in array data that overcomes some
of the problems with clustergrams / dendrograms, where a given row or column
may only belong in a single cluster.
·
Pioneered “matrix tile analysis”, the
problem of decomposing a data matrix into a set of non-overlapping tiles, each
of which is defined by a subset of rows and columns with no element belonging
to more than one tile, in order to find multi-way associations in the
data. This work was motivated by
the desire to find protein complexes and pathways in gene interaction and gene
expression data.
Google
Engineering Intern Summer
2006
Google, Mountain View, California
Advisor: Ashutosh Garg
·
Developed machine learning algorithms
for performing computer vision tasks for mobile device applications. Details of the project cannot be
disclosed under NDA.
Microsoft
Research Intern Summer
2005
Microsoft
Research, Machine Learning and Applied Statistics,
Redmond, Washington
Advisor: Nebojsa Jojic
·
Developed machine learning algorithms
for solving a variety of computer vision tasks, aiming for the algorithms to be
as generally applicable as possible so that they were not tailored specifically
to solve just one particular task or work in only very special cases.
·
Modelling long distance correlations
in patch based probabilistic graphical models was found to be important in
manipulating the illumination of an image and in mimicking a physical
walkthrough of an image. In both
cases, the task was performed given only a single image and no knowledge of
geometry.
·
Sub-modular clustering was found to be
useful for video segmentation.
·
The use of video epitomes in
performing biological cell tracking was examined.
NSERC
Undergraduate Student Research Award Recipient Summer
2002
University
of Manitoba, Dept. Elec. & Comp. Eng.,
Winnipeg, Manitoba
Advisor: Witold Kinsner
·
Researched the application of advanced
computer engineering techniques to digital signal processing in order to
analyze stochastic, non-stationary, self-similar signals such as
electroencephalograms (EEGs), speech, and Internet traffic.
·
Developed Java programs for neural
networks, wavelets, fractal dimensions, distributed computing systems, genetic
algorithms, data compression, and information entropy.
·
Collaborated with Joseph Pear from the
University of Manitoba’s Psychology Department in analyzing spatio-temporal
behavioural signals of Siamese fighting fish when presented with various
stimuli during dishabituation experiments.
·
The signals were found to be fractal
in nature. Multifractal features
were extracted from the signals and used by several neural networks, including
probabilistic and complex domain neural networks, to perform classification of
the fish behaviours.
Publications
Journal
Articles
1.
V. Cheung, B. J. Frey, and N.
Jojic. Video Epitomes. Intern. Journal of Computer Vision
(IJCV), 2007 (to appear).
2.
W. Kinsner, V. Cheung, K. Cannons, J.
Pear, and T. Martin. Signal
Classification through Multifractal Analysis and Complex Domain Neural
Networks. IEEE Trans. on
Systems, Man, and Cybernetics (SMC), Part C, Vol.
36, No. 2, March 2006.
Refereed
Conference Papers
3.
V. Cheung, N. Jojic, D. Samaras. Capturing Long-Range Correlations with
Patch Models. In Proc. IEEE
Intern. Conf. Computer Vision and Pattern Recognition (CVPR), 2007.
4.
I. E. Givoni, V. Cheung, and B. J.
Frey. Matrix Tile Analysis. Uncertainty in Artificial
Intelligence (UAI), 2006.
5.
V. Cheung, B. J. Frey, and N.
Jojic. Video Epitomes. In Proc. IEEE Intern. Conf. Computer
Vision and Pattern Recognition (CVPR), 2005. (Best
paper honorable mention award)
6.
W. Kinsner, V. Cheung, K. Cannons, J.
Pear, and T. Martin. Signal
Classification through Multifractal Analysis and Complex Domain Neural
Networks. In Proc. IEEE Intern.
Conf. Cognitive Informatics, August 2003.
7.
V. Cheung, K. Cannons, W. Kinsner, and
J. Pear. Signal Classification
through Multifractal Analysis and Complex Domain Neural Networks. In Proc. IEEE Canadian Conf. Elec.
and Comp. Eng., May 2003.
Technical
Reports
8. V. Cheung, I. E. Givoni, D. Dueck, and B. J. Frey. Factorgrams: A tool for visualizing
multi-way associations in biological data. University of Toronto Technical Report PSI-2006-44, May 15, 2006.
Presentations
Conference
Talks
1.
“Video Epitomes”, IEEE Intern. Conf.
Computer Vision and Pattern Recognition (CVPR), San Diego, June 22, 2005.
2. “Signal Classification through Multifractal Analysis and Complex
Domain Neural Networks”, IEEE Canadian Conf. Elec. and Comp. Eng., Montreal,
May 5, 2003.
Invited Talks
3.
“Video Epitomes”
a.
University of Windsor, Sept. 22, 2006.
b.
Google, Mountain View, California,
June 21, 2006.
c.
University of Manitoba, May 13, 2005.
d.
The Learning Workshop, Snowbird, Utah,
April 8, 2005.
4.
“Modelling Motion Patterns with Video
Epitomes”, Machine Learning Group Meeting, University of Toronto, Oct. 18,
2004.
5.
“Learning the ‘Epitome’ of a Video
Sequence”, Information Processing Workshop, University of Toronto, Aug. 11,
2004.
6. “An Introduction to Probabilistic Neural Networks”, Signal and Data
Compression Laboratory Group Meeting, University of Manitoba, June 10, 2002.
Teaching Experience
Guest
Lecturer – Neural Computation and Adaptive Perception Summer 2005
University
of Toronto, Dept. Computer Science, Toronto,
Ontario
Sponsored by: Canadian Institute for Advanced
Research (CIAR)
·
Presented prior work on epitomes as
generative models and my work on video epitomes.
Guest
Lecturer – Topics in Machine Learning: Natural Scene Statistics Spring 2005
University
of Toronto, Dept. Computer Science, Toronto,
Ontario
Instructor: Richard Zemel
·
Presented an introduction to Markov
Random Fields and texture analysis.
Computer
Tutor 1999
- 2003
MicroAge
Technology Services, Winnipeg, Manitoba
·
Gave tutorial sessions to customers on
basic e-mail and web browsing usage.
More in-depth lessons taught operability within Microsoft Office’s Word,
Excel, and PowerPoint.
Professional Activities
·
Reviewer for IEEE Intern. Conf. on
Computer Vision (ICCV), IEEE Intern. Conf. on Computer Vision and Pattern
Recognition (CVPR), IEEE Trans. Pattern Analysis and Machine Intelligence
(PAMI), Uncertainty in Artificial Intelligence (UAI), IEEE Trans. Systems, Man,
and Cybernetics (SMC), IEEE Trans. Circuits and Systems for Video Technology
(TCSVT)
·
Volunteer IEEE Canadian Conf. on Elec.
& Comp. Eng., 2002, Winnipeg, MB
·
Volunteer IEEE Canadian Conf. on Comp.
& Soft. Eng. Education, 2002, Winnipeg, MB
Additional Experience
Computer
Technician 1995
- 2003
MicroAge
Technology Services, Winnipeg, Manitoba
·
Conducted troubleshooting and repaired
hardware and software problems.
·
Assisted in the accounting and
managerial areas.
Joint
Owner 1998
- 2003
TVKMLMC
Vending, Winnipeg, Manitoba
·
Operated and maintained a vending
machine and tracked weekly sales
Pursue
Your Calling Scholarship Summer Student Summer
2001
Manitoba Telecom
Services, Winnipeg, Manitoba
·
Developed databases and designed web
pages to access these databases.
Processing
Support Analyst Summer
2000
Manitoba
Hydro, Winnipeg, Manitoba
·
Serviced numerous internal clients by
resolving their computer hardware, operating system, and software application
problems.
Technical Skills
Programming
Languages
·
Java, C, C++, C#, Visual Basic,
Matlab, Assembly, VHDL, LaTeX, CSS, HTML, SQL, network and concurrent
programming
Software
·
Digital and analog circuit CAD tools
(Xilinx ISE, ModelSim, Altera Max Plus II, ORCAD, PSpice), drafting CAD tools
(AutoCAD)
Interests
·
Indoor and beach volleyball
enthusiast, playing several times a week
·
Enjoys rollerblading, ice skating,
snowboarding, skiing, basketball, white water rafting, dragon boat racing,
curling, indoor rock climbing, running, table tennis, ultimate, travelling (4
continents, 18 countries)
References
1. Brendan J. Frey, Associate Professor Tel: 416-978-7001
Dept. Elec. & Comp. Eng., University of Toronto frey@psi.toronto.edu
10 King’s College Rd., Toronto, ON
M5S 3G4
2. Nebojsa Jojic, Researcher Tel: 425-705-5865
Machine Learning and Applied Statistics, Microsoft Research jojic@microsoft.com
One Microsoft Way, Redmond, WA
98052
3. Witold Kinsner, Associate Head of Computer Engineering Tel: 204-474-6490
Dept. Elec. & Comp. Eng., University of Manitoba kinsner@ee.umanitoba.ca
15 Gillson St., Winnipeg, MB R3T
5V6
4. Charlie Boone, Professor Tel:
416-946-7260
Dept. Medical Research, University of Toronto charlie.boone@utoronto.ca
160 College St., Toronto, ON M5S
3E1