CIS 680-301, Vision and Learning, Spring 2005

Time & Place: TR 430pm-6:00pm, Towne 303
Instructor: Jianbo Shi, jshi@cis.upenn.edu

Course Description

In recent years, we have seen a convergence between machine vision and machine learning. The combination of the machine learning techniques with the right vision routines, have produced impressive results in object tracking, face detection, and object recognition. At the same time, successful though somewhat ad hoc vision algorithms have provided new insights to many machine learning problems.

In this course, we will explore this connection between vision and learning. We will cover topics in 1) image texture synthesis; 2) object detection and segmentation; 3) dynamic object tracking; 4) object and scene recognition; 5) human activity recognition and inference.

Project

Course Schedule

Date

Topics Papers Discussion

1/13

Texture: synthesis- a practical guide

Efros, Hertzmann, Shum

  here

1/18

Texture: analysis-image statistics, similar measure

Martin & Fowlkes & Malik,
Rubner & Tomasi & Guibas,
Puzicha et.al.

 

1/20

Texture: synthesis/analysis: probabilistic formulation

Zhu & Wu & Mumford,

 

1/25

Texture: synthesis/analysis: probabilistic formulation

Portilla & Simoncelli

 
1/27 Object Detection: face detection- statistical approaches Scheinderman & Kanade,
Viola & Jones
2/1 Object Detection: more on boosting & bagging Freund & Schapire
breiman

2/3

Object Detection: flexible object detection via Graphical Models

Ioffe & Forsyth

2/8

Object Detection: flexible object detection via Graphical Models

Felzenszwalb & Huttenlocher

2/10

Object Detection: efficient inference procedures for Graphical models(HMM, Tree, MRF):

Tutorial, Ghahramani & Jordan,
Smyth &Heckerman,

 

2/15

Object Detection: Learning graphical models from examples

Song & Goncalves & Perona
Fergus, Perona, & Zisserman

 

2/17

Object Detection: Review on EM, HMM

Bilmes

 

2/22

Object Detection: variational approach for graph inference

Jordan & Ghahramani & Jaakkola & Saul
Saul, et.al.

 
2/22 Object Tracking: Sampling, particle filtering Isard & Blake
Cham & Rehg

2/24

Object Tracking: Markov Chain Monte Carlo(MCMC) methods

Crisan & Doucet
Tu & Zhu

 

3/1

Image Representation: PCA, ICA, Mixture Models

Bell & Sejnowski
Roweis & Ghahramani
 

3/15

Image Representation: Learning Image Features

Lee & Seung
Stauffer & Grimson
 
3/16 Object Recognition: Digit Recognition with Shape Context, Belongie, Malik, Puzicha

3/17

Object Recognition: Digit/Face Recognition, Support Vector Machine(SVM),

Burges
Vapnik,

 

3/22

Object Recognition: Neutral Net,

LeCun,  

3/24

Object Recognition: Neutral Net,

LeCun,  

3/29

Object Recognition: Multi-class Object Recognition

Mahamud, Hebert and Lafferty  

3/31

Grouping: Object Segmentation: Graph cuts approaches

Shi, Malik,
 

4/5

Grouping: Object Segmentation: Graph cuts approaches, Multiscale Graph Cuts

sharon, Brandt, Basri  

4/7

Grouping: Stereophesis, Image labeling: Markov Random Field, and Graph Cuts

Ishikawa Geiger, Boykov, Veksler, Zabih  

4/12

Grouping: Grouping with Partial labeling

Yu & Shi  

4/14

Grouping: Co-Training, knowledge transfer

Barnard, et. al., Blum & Mitchell,  

4/22(class Tu. cancelled)

Action Recognition: Learning Grammatical models of Human Actions

Moore & Essa  

4/26

Review

   

Course Format

This course consists of three components:

There is no class final examine. Project 70%, Selected topic discussion 20%, Class participation: 10%.

References

  • Vision Books:
  • Machine Learning Books:
  • Matlab:
  • On-line Discussion: Quicktopic.com

  • last updated by jshi on January 13, 2005