Angjoo Kanazawa Education Academic Research Experience

Copy and paste this link to your website, so they can see this document directly without any plugins.


University, Computer, Angjoo, David, York, Research, Kanazawa,, Advisor:, 2016, College, York,, Science, Park,, Jacobs,, Vision, Intern, 2011, using, September, Developed, August, 2014, system, 2010, 2012, from, Maryland,, Maryland, Jacobs, Assistant


Angjoo Kanazawa
4453 A. V. Williams Bldg. phone: 301-405-1750
Department of Computer Science
University of Maryland
College Park, MD 20742
University of Maryland, College Park College Park, MD, USA
PhD in Computer Science expected May 2017
– Advisor: Dr. David Jacobs
New York University New York, NY, USA
B.A in Computer Science and Mathematics, Magna Cum Laude May, 2011
– Advisor: Dr. Rob Fergus
Academic Research Experience
Research Intern Tübingen, Germany
Max Planck Institute for Intelligent Systems, Perceiving Systems Dept January 2016 - July 2016
– Advisor: Michael Black
– Worked on a completely automatic method for single-view reconstruction of humans using the
SMPL body model and a state of the art human pose detection ConvNet.
Research Intern Cupertino, CA
NEC Labs America June 2015 - September 2015
– Advisor: Manmohan Chandraker
– Worked on weakly supervised single view reconstruction of birds. Developed and trained a novel
ConvNet architecture whose output serves as a spatial prior for finding correspondence between
two bird images.
Graduate Research Assistant College Park, MD
Center for Automation Research, University of Maryland June 2012 - Present
– Advisor: David Jacobs
– Developed a method to learn 3D deformation of animals, specifically cats and horses, from
annotated 2D images.
– Developed scale-invariant deep convolutional networks
– Improved a large-scale object detection system utilizing ideas from fine-grained classification.
Graduate Research Assistant New York, NY
Columbia University June 2012 - August 2012
– Advisor: Peter Belhumeur and David Jacobs
– Develop a method based on random fern regressor to localize landmark of faces, dogs, and birds
for fine-grained classification
Undergraduate Research Assistant New York, NY
Courant Institute of Mathematics, NYU September 2010 - May 2011
– Advisor: Rob Fergus
– Improved an automatic diagnosis system for a diabetic eye disease with various machine learning
techniques such as SVM, quadratic optimization, and artificial neural networks.
3D Menagerie: Modeling the 3D shape and pose of animals Silvia Zuffi, Angjoo Kanazawa,
David Jacobs, Michael J. Black Arxiv 2016
Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image
Federica Bogo*, Angjoo Kanazawa*, Christoph Lassner, Peter Gehler, Javier Romero, Michael J.
Black (* equal contribution) ECCV 2016
WarpNet: Weakly Supervised Matching for Single-View Reconstruction Angjoo Kanazawa,
David Jacobs, Manmohan Chandraker CVPR 2016
Learning 3D Articulation and Deformation using 2D Images Angjoo Kanazawa, Shahar
Kovalsky, Ronen Basri, David Jacobs, Eurographics 2016
Günter Enderle Best Paper Award
Locally Scale-invariant Convolutional Neural Network Angjoo Kanazawa, Abhishek Sharma,
David Jacobs, Deep Learning and Representation Learning Workshop: NIPS 2014
Affordance of Object Parts from Geometric Features Austin Myers, Angjoo Kanazawa, Cornelia Fermuller, Yiannis Aloimonos, RGB-D: Advanced Reasoning with Depth Cameras: RSS 2014,
Vision Meets Cognition Workshop: CVPR 2014
Dog Breed Classification using Part Localization Jiongxin Liu, Angjoo Kanazawa, Peter Belhumeur, David Jacobs, ECCV, 2012.
Employment History
Software Engineering Intern Mountain View, CA
Google X, Self-driving Car Team May 2014 - August 2014
– Developed a Computer Vision system to recognize visual occluders.
Technology Summer Analyst New York, NY
Goldman Sachs May 2010 - August 2010
– Implemented a backward compatible serialization system for archiving large-scale data efficiently.
Web Developer New York, NY
New York University Wagner School of Public Service September 2009 - May 2010
Software Engineer Intern New York, NY
IndustryNext, LLC May 2009 - August 2009
Detecting Out-of-Focus Images, Angjoo Kanazawa, Wan-Yen Lo, Abhijit Ogale, in preparation.
Dog Breed Classification using Part Localization, the 7th International Workshop on Robust
Computer Vision (IWRCV), Osaka University, Japan, January 2013
Explicit Shape Regression, the Computer Vision Student Seminar, University of Maryland, College Park, September 2012
Teaching Experience
Spring 2012: (CMSC421) Introduction to Artificial Intelligence, University of Maryland
Fall 2011: (CMSC131) Object-Oriented Programming I, University of Maryland
Fall 2008-Spring 2009: (CSCI-UA.0101,103) Introduction to Computer Science I, II, New York
Programming Skills
C/C++, CUDA, MATLAB, Python, Java, Javascript, Objective-C, Emacs, LATEX, Linux
Honors and Awards
Günter Enderle Best Paper Award, Eurographics 2016
Graduate Student Summer Research Fellowship, University of Maryland, College Park, 2013
Block Fellowship, Computer Science Department, University of Maryland, College Park, 2011-2013
Google Anita Borg Memorial Scholarship, 2011
Computer Science Prize for Academic Excellence and Service to the Department, New York University, 2011
Dean’s List of Distinguished Students, New York University, 2009-2011
Organizer of the UMD Computer Vision Student Seminar 2012-2015
President of Women in Computing, New York University 2009-2011
Vice President of ACM, New York University 2010-2011
International Collegiate Programming Competition, 2008-2011

PDF Document reader online

This website is focused on providing document in readable format, online without need to install any type of software on your computer. If you are using thin client, or are not allowed to install document reader of particular type, this application may come in hand for you. Simply upload your document, and will transform it into readable format in a few seconds. Why choose

  1. Unlimited sharing - you can upload document of any size. If we are able to convert it into readable format, you have it here - saved for later or immediate reading
  2. Cross-platform - no compromised when reading your document. We support most of modern browers without the need of installing any of external plugins. If your device can oper a browser - then you can read any document on it
  3. Simple uploading - no need to register. Just enter your email, title of document and select the file, we do the rest. Once the document is ready for you, you will receive automatic email from us.

Previous 10

Next 10