CIS 700/002, Vision and Learning, Spring 2003

CIS 700-002, Vision and Learning, Spring 2003

Time & Place: MW 430pm-6:00pm, Towne 305
Instructor: Jianbo Shi, jshi@cis.upenn.edu
Note: the project page is up: here .

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.

Course Schedule

Date	Topics	Papers	Discussion
1/13	Texture: synthesis- a practical guide	Efros, Hertzmann, Shum	here
1/15	Texture: analysis-image statistics, similar measure	Martin & Fowlkes & Malik, Rubner & Tomasi & Guibas, Puzicha et.al.
1/22	Texture: synthesis/analysis: probabilistic formulation	Zhu & Wu & Mumford, Portilla & Simoncelli
1/27	Object Detection: face detection- statistical approaches	Scheinderman & Kanade, Viola & Jones
2/3	Object Detection: more on boosting & bagging	Freund & Schapire breiman
2/5	Object Detection: flexible object detection via Graphical Models	Ioffe & Forsyth Felzenszwalb & Huttenlocher
2/10	Object Detection: efficient inference procedures for Graphical models(HMM, Tree, MRF):	Ghahramani & Jordan, Smyth &Heckerman, Jordan & Ghahramani & Jaakkola & Saul
2/12	Object Detection: Learning graphical models from examples	Song & Goncalves & Perona Meila & Jordan
2/19	Object Tracking: Sampling, particle filtering	Isard & Blake Cham & Rehg
2/24	Object Tracking: Markov Chain Monte Carlo(MCMC) methods	Crisan & Doucet Tu & Zhu
2/26	Image Representation: PCA, ICA, Mixture Models	Bell & Sejnowski Roweis & Ghahramani
3/3	Image Representation: Learning Image Features	Lee & Seung Stauffer & Grimson
3/17	Object Recognition: Digit/Face Recognition, Support Vector Machine(SVM),	Burges Vapnik,
3/19	Object Recognition: Neutral Net, Digit Recognition with Shape Context,	LeCun, Belongie, Malik, Puzicha
3/24	Object Recognition: Multi-class Object Recognition	Mahamud, Hebert and Lafferty
3/26	Grouping: Object Segmentation: Graph cuts approaches	Shi, Malik, sharon, Brandt, Basri
3/31	Grouping: Stereophesis, Image labeling: Markov Random Field, and Graph Cuts	Ishikawa Geiger, Boykov, Veksler, Zabih
4/9	Grouping: Learning to Segment, Learning with Partial labeling	Barnard, et. al.
4/11	Grouping: Co-Training, knowledge transfer
4/14	Action Recognition: Recognizing Human Movements
4/16	Action Recognition: Learning Grammatical models of Human Actions
4/21	Action Recognition: Vision and Sound: Lip Reading
4/23	Action Recognition: Automatic Video Summarization
	Power-law in Large Dataset
	Scene Recognition with Large Dataset
final	Project presentation

Course Format

This course consists of three components:

1) Course lectures. A tentative class schedule is listed above. A set of reference papers will be posted before each lecture.
On-line discussions on selected lecture topics. To encourage people to ask questions and get more out of each topic, an on-line discussion group will be created.Details of how to sign on can be found here. Each student is expected to lead one discussion topic. A written report is due one week after the lecture is given. I will email each of you the topic that you will lead.
3) Projects. There are two projects, one pre-assigned project due on March 15, and one open project due on May 1. Projects could be done in a team of no more than two. The proposal for the final project is due no later than March 6.

There is no class final examine. Final project: 40%, Mid-term project 30%, Selected topic discussion 20%, Class participation: 10%.

References

Vision Books:

Forsyth and Ponce, Computer Vision -- A Modern Approach
Trucco and Verri, Introductory Techniques for 3-D Computer Vision

Machine Learning Books:

Chris Bishop, Neural Networks for Pattern Recognition
Duda and Hart and Stork, pattern Classification

Matlab:

On-line Discussion: Quicktopic.com

last updated by jshi on January 14, 2003