Click here to start

Table of contents

MIT 6.899 Learning and Inference in Vision

Reading class

Learning and Inference

Slide 4

Slide 5

Slide 6

Cartoon history of speech recognition research

Same story for document understanding

Computer vision is ready to make that transition

Categories of the papers

1 Learning image representations

Slide 12

2 Learning manifolds

Slide 14

Slide 15

3 Linear and bilinear models

4 Learning low-level vision

5 Graphical models, belief propagation

6 Particle filters and tracking

7 Face and object recognition

Slide 21

Slide 22

8 Learning models of object appearance

Slide 24

8 Learning models of object appearance

Guest lecturers/discussants

Class requirements

1. Read the papers, discuss them

2. Presentations about a paper

3. Programming example

Toy problems

Toy problem

Slide 33

Particle filter for inferring human motion in 3-d

Particle filter toy example

What we’ll have at the end of the class

4. Final project: write a conference paper

Feedback options

What background do you need?

Auditing versus credit

First paper

Second paper

Author: Michael Ross