<? echo $GLOBALS['title'] ?>

Academics


CAP 5415 (Computer Vision), Fall 2008
An elementary course on Computer Vision offered by Dr. Marshall Tappen. I learned various image processing techniques, image understanding and statistical methods for machine learning. These included Fourier Transforms, Image Sharpening, Blurring, Edge Detection, Support Vector Regression, K-means clustering, Stereo Vision, Camera Calibration and so on. Here are the assignment and project report that I think could be useful.

MAP 6938 (Mathematical Methods on Image Analysis), Fall 2008
This is an advanced level course offered by Dr. Xin Li from the Mathematics Department. The main objective of the course was to develop detailed insight on some of the mathematical tools used in Computer Vision and Image Processing. I learned to use Principal Component Analysis for Face recognition, Correlation Filters (MACH filters) for Automatic Target Recognition, Compressive Sampling for Exact/Near Exact Signal Recovery, Eigen decomposition, Linear Algebra, Frequency domain image transformations, Diffusion Maps for Dimensionality Reduction, Level Sets method, Determining Optical Flow for tracking and much more. Here are the assignment and project reports that I think could be useful.
  • Eigenvalue problems and Principal Component Analysis M. Turk, A. Pentland, Eigenfaces for Recognition, Journal of Cognitive Neurosicence, Vol. 3, No. 1, 1991, pp. 71-86
  • Correlation and MACH filters Abhijit Mahalanobis, B. V. K. Vijaya Kumar, Sewoong Song, S. R. F. Sims, and J. F. Epperson, Unconstrainted Correlation Filters, Applied Optics, 33(1994), 3751-3759
  • Signal Recovery Compressive Sampling Emmanuel Candès, Justin Romberg, and Terence Tao, Stable signal recovery from incomplete and inaccurate measurements. (Communications on Pure and Applied Mathematics, 59(8), pp. 1207-1223, August 2006)
  • Diffusion MapsR.R. Coifman, S. Lafon, “Diffusion maps,” Applied and Computational Harmonic Analysis: Special issue on Diffusion Maps and Wavelets, Vol 21, July 2006, pp 5-30.
  • Level Sets Method and Optical Flow AnalysisS. J. Osher and R. Fedkiw, Level Set Methods and Dynamic Implicit Surfaces, Springer, 2002.

CAP 6412 (Advanced Computer Vision), Fall 2008
My advisor Dr. Mubarak Shah recommended me to audit this course. This too was a great learning experience. We discussed a lot of papers and we were required to write our own version of a review for each of these papers. We were also required to do a project. Here are the papers that we discussed and their corresponding reports.
  • Arslan Basharat, Alexei Gritai, and Mubarak Shah, "Learning Object Motion Patterns for Anomaly Detection and Improved Object Detection", CVPR 2008.
  • Y. Pritch, A. Rav-Acha, S. Peleg, "Video Synopsis and Indexing", PAMI 2008 Report
  • H. Jiang, D. Martin, "Finding Actions Using Shape Flows", EECV 2008. Report
  • T. Leyvand, D. Cohen-Or, G. Dror, D. Lischinski, "Data-Driven Enhancement of Facial Attractiveness", SIGGRAPH 2008. Report
  • Yanlin Guo,Steve Hsu, Harpreet S. Sawhney, Rakesh Kumar, and Ying Shan, "Robust Object Matching for Persistent Tracking with Heterogeneous Features", PAMI 2007. Report
  • Jiangjian Xiao, Hui Cheng, Feng Han, Harpreet Sawhney, "Geo-spatial Aerial Video Processing for Scene Understanding and Object Tracking", CVPR 2008. Report
  • James Hays, and Alexei A. Efros, "IM2GPS: Estimating Geographic Information from a Single Image", CVPR 2008. Report
  • Christoph H. Lampert, Matthew B. Blaschko, Thomas Hofmann, "Beyond Sliding Windows: Object Localization by Efficient Subwindow Search", CVPR 2008. Report
  • P. Lagger, M. Salzmann, V. Lepetit, and P. Fua, "3D Pose Refinement from Reflections", CVPR 2008 Report
  • Zivkovic, Zoran and Heijden van der, Ferdinand, "Recursive unsupervised learning of finite mixture models", PAMI 2004 Report
  • P. Tu, T. Sebastian, G. Doretto, N. Krahnstoever, J. Rittscher, and T. Yu, "Unified Crowd Segmentation", ECCV 2008. Report
  • Mykhaylo Andriluka, Stefan Roth, Bernt Schiele, "People-Tracking-by-Detection and People-Detection-by-Tracking", CVPR 2008. Report
  • H. Wu, X. Liu, G. Doretto. "Face Alignment using Boosted Ranking Models." In Proc. of IEEE CVPR, 2008 Report
  • Ivan Laptev, Marcin Marszałek, Cordelia Schmid, Benjamin Rozenfeld, "Learning realistic human actions from movies", CVPR 2008.Report
  • Zhuowen Tu, "Auto-context and Its Application to High-level Vision Tasks" , In Proc. of IEEE CVPR, 2008
  • Engin Tola, Vincent Lepetit, Pascal Fua, "A Fast Local Descriptor for Dense Matching", In Proc. of IEEE CVPR, 2008
  • Gunhee Kim, Christos Faloutsos, Martial Hebert, "Unsupervised Modeling of Object Categories Using Link Analysis Techniques", In Proc. of IEEE CVPR, 2008
  • L. Yang, R. Jin, R. Sukthankar, F. Jurie. "Unifying Discriminative Visual Codebook Generation with Classifier Training for Object Category Recognition", In Proc. of IEEE CVPR, 2008