Vision and AI Research Group
Korean Graduate Students in  CS@UMD

 (aster & swjoo)

 (bhhan)

Focus on Ahmed's paper

(knkim)

Focus on Eigenfaces paper

(aster)

(swjoo)

• Seong-Wook Joo, An Overview of Markov Random Field: Theory and Application
  

• Stan Z. Li, Chapter1, Markov Random Field Modeling in Computer Vision, 
  http://research.microsoft.com/~szli/MRF_Book/MRF_Book.html
  

• Stan Z. Li, Modeling Image Analysis Problems Using Markov Random Fields (2000), http://citeseer.nj.nec.com/li00modeling.html
  

• Charles A. Bouman, Markov Random Fields and Stochastic Image Models http://www.ece.purdue.edu/~bouman/publications/mrf_tutorial/view.pdf

(bhhan)

• Bohyung Han, "Mean-Shift Algorithm and Its Application"
  
• D. Comaniciu, V. Ramesh, P. Meer: Kernel-Based Object Tracking, IEEE Trans. Pattern Analysis Machine Intell., Vol. 25, No. 5, 564-575, 2003
• D. Comaniciu: An Algorithm for Data-Driven Bandwidth Selection, IEEE Trans. Pattern Analysis Machine Intell., Vol. 25, No. 2, 281-288, 2003
• D. Comaniciu, P. Meer: Mean Shift: A Robust Approach toward Feature Space Analysis, IEEE Trans. Pattern Analysis Machine Intell., Vol. 24, No. 5, 603-619, 2002

All of three papers are from PAMI, and you can download at http://www.caip.rutgers.edu/~comanici/

(knkim)

• UMD, CMSC 828D: Fundamentals of Computer Vision (Fall 2000),       Lecture1:  Introduction. Course overview. Introduction to Matlab
• David Forsyth, Lecture 1: A broad introduction to the ideas and methods of vision. An Introduction to Computer Vision
• http://www.umiacs.umd.edu/~ramani/cmsc828d/segmentation.pdf
• Deformable/Active Contours (or Snakes)
• CMU Tai Sing Lee's lectures
  • Snake (Aactive Contours)
  • Active Shape Model

overview of computer vision 

segmentation with 'snake'

(aster)

• Hyoungjune Yi, Bayesian Networks
  
• www.umiacs.umd.edu/~bonnie/courses/cmsc421-02/bns.ps, This tutotial is written by Professor Daphne Koller (Stanford) and respected as a bible of BN.

Support Vector Machine (SVM)

(swjoo)

• Seong-Wook Joo, Linear Discriminant Functions and SVM
  
• Duda, Hart, and Stork, "Pattern Classification" Chapter 5, Wiley, 2000
• C. J. C. Burges. A Tutorial on Support Vector Machines for Pattern Recognition. Knowledge Discovery and Data Mining, 2(2), 1998 http://www.kernel-machines.org/papers/Burges98.ps.gz
  http://www.cfar.umd.edu/~shaohua/enee739q_cmsc858c/svm_pr_tutorial.pdf
• Bernhard Scholkopf and Alexander J. Smola, "Learning with Kernels - Support Vector Machines, Regularization, Optimization, and Beyond", MIT Press, 2002, Chapter 1 http://www.learning-with-kernels.org/sections/

(bhhan)

• Bohyung Han, "Particle Filtering for Non-Linear/Non-Gaussian System"
  
• We need to take a look at Kalman filter and its extensions (EKF). The homepage about Kalman filter is http://www.cs.unc.edu/~welch/kalman/
• This page include a quick reference about Kalman filter and Extended Kalman filter, "An Introduction to the Kalman Filter," and the link is http://www.cs.unc.edu/~welch/kalman/kalmanIntro.html
• We will only brush up on the basic concept about Kalman filter stuff and move to condensation.
• The condensation homepage is very helpful for us. http://www.dai.ed.ac.uk/CVonline/LOCAL_COPIES/ISARD1/condensation.html
• There are several papers listed, and the most fundemental and detailed version is "CONDENSATION - conditional density propagation for visual tracking, IJCV."
• A good tutorial of the particle filter is "A Tutorial on Particle Filters for On-line Non-linear/Non-gaussian Bayesian Tracking." This paper covers most variations of particle filter, but we will talk about only basic particle filtering at this time. 

(kiyoon)

• Kyongil Yoon, "Segmentation"
  
• David A. Forsyth, Jean Ponce, Computer Vision: A Modern Approach, Prentice Hall, 2003, Chap 14, 15, 16, 17
• Chapter 14: Segmentation by clustering
• Chapter 15: Segmentation by fitting a model
• Chapter 16: Segmentation and fitting using probabilistic methods
• Chapter 17: Tracking with linear dynamic models

(knkim)

• Will be placed after publication

• Go for eat-out?

(all members)

• Keep working on background materials
  
• Select and study good research papers related to our interests
  
• Present each member's research topic.

(sbw)

•  Face Recognition: A Literature Survey (http://citeseer.nj.nec.com/zhao00face.html)
  
•  A Survey of Face Recognition ( http://citeseer.nj.nec.com/fromherz97survey.html )

canceled

'bhhan' presented his research work

(swjoo)

• Seong-Wook Joo, Stereo 3D Reconstruction
  
• References for stereo:"Multiple View Geometry in Computer Vision" http://www.robots.ox.ac.uk/~vgg/hzbook.html, Chapter on "Epipolar Geometry and the Fundamental Matrix" 
  
• Shape from motion (factorization method): "Shape and Motion from Image Streams: a Factorization Method", Tomasi and Kanade http://citeseer.nj.nec.com/221713.html

(aster)

• Hyoungjune Yi, "Multimedia for our time (For Dummies)"
   
• http://www.m4if.org/resources/IEEESpectrum/mpeg-4.htm
  
• MPEG-4 Multimedia for our time - IEEE Spectrum

• Title: 3D Facial Features and Motion Recovery using SVD and multi-modal information
  
  Speaker: Dr. Sang Hoon Kim, Hankyong National University, Kyonggi-Do, Korea

(kiyoon)

• Kyongil Yoon, "Color"

(knkim)

• Kyungnam Kim's presentation material reviewing the following paper:

(bhhan)

• Bohyung Han, "Tracking with Online Appearance Model"
  
• A. Jepson, D. Fleet, T. El-Maraghi, Robust online appearance models for visual tracking, IEEE Conf. Computer Vision and Pattern Recognition (CVPR'01), Hawaii, vol. 1, 415-422, 2001 http://www2.parc.com/spl/members/fleet/research/Papers/cvpr-01A.pdf
• S. Zhou, R. Chellappa, B. Moghaddam., Appearance tracking using adaptive models in a particle filter, Asian Conference on Computer Vision (ACCV), January 2004 http://www.cfar.umd.edu/~shaohua/papers/zhou04accv.pdf

(swjoo)

• Seong-Wook Joo, "3D reconstruction - Factorization Method" (Presentation slides),  (PDF report)
  
• I will talk about the famous "Factorization method" for structure from motion. http://vision.stanford.edu/public/publication/tomasi/tomasiTr92Text.pdf. Subspace methods in general will also be discussed.

Shape

(aster)

Optical Illusions

(kiyoon)

• Kyongil Yoon, "Optical Illusions"

Performance Evaluation in Computer Vision

(knkim)

• VS-PETS2003 slides, "A Perturbation Method for Evaluating Background Subtraction Algorithms
  
• Kyungnam Kim's presentation reviewing the following papers:

(swjoo)

(swjoo)

Continued....