DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING
UNIVERSITY OF CALIFORNIA, SAN DIEGO
Students taking the course for four units should follow these project guidelines. Here is the feedback form for presentations.
Please read, reflect upon, and follow these presentation guidelines, kindly provided by Prof. Elkan. Immediately after your presentation, please email to sjb@cs a copy of your slides. For ease of viewing, please make this copy be two slides per page in Adobe PDF.
The schedule of papers and presentations is below. Participants who have not chosen a paper yet should look at the list of suggested papers and contact the instructor.
If you want to change your presentation date, please arrange a swap with another student and notify the instructor at least two weeks in advance.
date 
presenter 
paper title 
author(s) 
discussion 
slides 
Sept. 20 
organizational meeting 




Sept. 25 
Ian Fasel 
Nonlinear component analysis as a kernel eigenvalue problem  Schoelkopf, B.; Smola, A.; Mueller, K.R.  
Sept. 27 
Joe Drish 
B. Schoelkopf, S. Mika, C.J.C. Burges, P. Knirsch, K.R. Mueller, G. Raetsch, and A.J. Smola 

Oct. 2  Andrew Cosand  A direct method for stereo correspondence based on singular value decomposition / An Algorithm for Associating the Features of Two Images  Pilu, M. / Guy L. Scott, H. Christopher LonguetHiggins  
Oct. 4  HsinHao Yu  Regularization theory and neural networks architectures  Girosi, F.; Jones, M.; Poggio, T.  
Oct. 9  Sameer Agarwal  Normalized cuts and image segmentation / Segmentation using eigenvectors: a unifying view  J. Shi and J. Malik / Y. Weiss  
Oct. 11  Markus Herrgard 
Learning
Segmentation with Random Walks / A Random Walks
View of Spectral Segmentation Matlab code: rw_seg.m ncut_rw_demo.m 
Meila, M. and Shi, J.  
Oct. 16  no meeting  
Oct. 18  Francis Quek  Special guest lecture:``Multimodal Discourse: Gesture, Speech and Gaze'' (Note room change: AP&M 4301) 


Oct. 23 
Ian Fasel 
Experiments with a New Boosting Algorithm / Improved Boosting Algorithms Using Confidencerated Predictions  Freund and Schapire / Schapire and Singer  
Oct. 25  Victor Gidofalvi  Robust Real Time Object Detection  Paul Viola and Mike Jones  
Oct. 30  Dave Kauchak  Empirical Evaluation of Dissimilarity Measures for Color and Texture  Jan Puzicha, Yossi Rubner, Carlo Tomasi and Joachim M. Buhmann  
Nov. 1  Andrew Cosand  Determining optical flow / An iterative image registration technique with an application to stereo vision  B. K. P. Horn and B. G. Schunck / Lucas, B. D. and Kanade, T.  
Nov. 6  Sameer Agarwal  Elements of Statistical Learning Theory, Ch. 5 of Learning with Kernels  Schölkopf and Smola  
Nov. 8  HsinHao Yu  A TwoLayer Sparse Coding Model Learns Simple and Complex Cell Receptive Fields and Topography from Natural Images.  A. Hyvärinen and P. O. Hoyer  
Nov. 13  Junwen Wu  A computer algorithm for reconstructing a scene from two projections  H.C. LonguetHiggins  
Nov. 15  Victor Gidofalvi  Texture synthesis by nonparametric sampling / Image Quilting for Texture Synthesis and Transfer  Efros and Leung / Efros and Freeman  
Nov. 20  Anand Subramaniam 
Learning and Recognizing human dynamics in Video Sequences Kalman Filter and EM applets: zip 
C. Bregler  
Nov. 22  Thanksgiving holiday  
Nov. 27  Dave Kauchak  Automatic Musical Genre Classification of Audio Signals  Tzanetakis, Essl, Cook  
Nov. 29  project presentations 
15 minute presentations (abstracts and reports) 
Agarwal / Cosand / Gidofalvi / Kauchak 
Relevant deadlines for students doing projects: ECCV 2002: Nov. 16, ICPR 2002: Dec. 1. TEXTURE 2002: Jan. 15,
CSE 291 is a graduate seminar devoted to recent research on pattern recognition and computer vision.
Students may enroll for one, two, or four units:
The seminar is open to anyone who has already taken at least one graduate course in computer vision, artificial intelligence, or a closely related area. Appropriate courses at UCSD include CSE 250A, CSE 250B, CSE 254, CSE 253, CogSci 202, ECE 270A, and CSE 275A.
The seminar will meet on Tuesdays and Thursdays from 11:10am12:30pm in 223 Center Hall. The first meeting will be on Thursday September 20, and the final meeting will be on Thursday November 29, 2001.
Possible topics include:
Students are encouraged to investigate both fundamental algorithmic issues as well as application areas such as biometrics, content based image retrieval, texture synthesis, motion capture, and image based rendering.
The instructor is Serge Belongie, Assistant Professor, AP&M room 4832.
Feel free to send email to sjb@cs with any questions.
Computer Vision  A Modern Approach, Forsyth and Ponce
Learning with Kernels, Schölkopf and Smola
Neural Networks for Pattern Recognition, Chris Bishop
Spectral Graph Theory, Fan Chung
Introductory Techniques for 3D Computer Vision Trucco and Verri
Pattern Classification Duda, Hart, and Stork
Pattern Recognition by Theodoridis and Koutroumbas
Kernel Machines Homepage
SVM Tutorial by Osuna, Freund, and Girosi
Lectures Notes on Machine Learning by Rivest and Singh
Each class meeting of 80 minutes will be divided into two parts. First, a student will give a talk lasting about 60 minutes presenting a recent technical paper in detail. In questions during the talk, and in the final 20 minutes, all seminar participants will discuss the paper and the issues raised by it.
Some papers will be theoretical, and some will be applied. Two related applications papers may be discussed together. Theoretical papers will typically be presented and discussed alone, to ensure that mathematical and algorithmic questions are discussed in sufficient depth.
In the first week, we will make a schedule of papers and presentations for the whole quarter. With 10 participants, each student will make two separate presentations. The procedure for one presentation is as follows:
Presentations will be evaluated, in a friendly way but with high standards. Each presentation should be prepared using LaTeX or Powerpoint. You should copy equations, diagrams, charts, and tables as necessary from the paper for the presentation.
For each presentation, we will have a webbased discussion area. Each seminar participant is expected to contribute at least one message to the discussion, before the presentation. A message may ask an interesting question, point out a strength or weakness of the paper, or answer a question asked by someone else. Messages should be thoughtful!
Each student will also do one term project following specific guidelines. The project should be at the frontier of current research, and preferably closely inspired by one of the papers discussed in the class. Project reports will be evaluated using these grading criteria. There is a schedule for handing in a detailed project proposal, a draft project report, and then the final report.
The seminar will have no final exam. Final grades will be based 50% on presentations and participation in class and in the webbased discussions. The other 50% will be the project report.
Acknowledgement: Special thanks to Charles Elkan, who kindly provided me with the web site template for his highly successful CSE254 seminar!
Most recently updated on Nov. 29, 2001 by Serge Belongie.