Reconnaissance d’objets et vision artificielle 2010/2011

Object recognition and computer vision 2010/2011


Jean Ponce, Ivan Laptev, Cordelia Schmid and Josef Sivic



Course Information

Room: ENS Ulm  Salle R aile Rataud 45 rue Ulm
Class time: Tuesday 16:15-19:15

Course description

Automated  object  recognition -- and  more  generally  scene  analysis -- from  photographs  and 
videos  is  the  grand  challenge  of  computer  vision.  This  course  presents  the  image,  object,  and 
scene models, as well as the methods and algorithms, used today to address this challenge.

Assignments

There will be four programming assignments representing 70% of the grade.

1. Scale invariant feature detection. Hand out date: Oct 5. Due date extended to: Oct 29.  
2. Stitching photo mosaics. Hand out date: Oct 12. Due date: Nov 2. 
3. Bag-of-features image classification. Hand out date: Nov 2. Due date: Nov 16.
4. Simple face detector. Hand out date: Nov 16. Due date: Nov 30.

Final project

The final project will represent 30% of the grade.

The topics will be announced in the class and on this page. Talk to us if you want to define your own project (before you start working on the project). Joint projects with other courses are possible, but please talk to instructors of both courses (before you start working on the project).  

Final projects are out.
Hand out date: Nov 2.  
Project presentations on: Dec 14. Schedule of the presentations is here.
Project reports due date extended to January 5th 2011


Computer vision and machine learning talks

You are welcome to attend seminars in the Willow group. Please see the current seminar schedule.
Typically, these are one hour research talks given by visiting speakers.
The talks are at 23 avenue d'Italie. Ring the bell to get into the building, then take the elevator to the 5th floor.

Course schedule (subject to change)

Lecture
 Date
 		Topic
 		Slides
1
 Sep 28
 Introduction (J. Ponce, I. Laptev, J. Sivic)

 PPT1 PPT2 PDF1 PDF2
2
 Oct 5
 Instance-level recognition I. - Local invariant features (C. Schmid)

Assignment 1 out. 		PPT1 PPT2 PDF1 PDF2
3
 Oct 12
 Instance-level recognition II. - Camera geometry (J. Ponce); Correspondence, efficient visual search (J. Sivic)

Assignment 2 out.
 		PPT1 PPT2 PPT3 
PDF1 PDF2 PDF3
Matlab tutorial scripts
4
 Oct 19
 Very large scale image indexing. Bag-of-feature models for category-level recognition (C. Schmid)

Assignment 1 due.  		PPT1 PPT2 PDF1 PDF2
5
 Oct 26
 Sparse coding and dictionary learning for image analysis (J. Ponce) 
Efficient visual search - extensions and applications (J. Sivic)

 		PPT1 PPT2 PDF1 PDF2
6 Nov 2
 Category-level localization; Efficient fitting of pictorial structures using distance transform (J. Sivic)

Assignment 2 due. Assignment 3 out. Final projects out. 		PDF
7 Nov 9
 Motion and human actions I. (I. Laptev)

 		PDF
8 Nov 16
 Motion and human actions II. (I. Laptev)

Assignment 3 due. Assignment 4 out. 		PDF
9
 Nov 23
 Neural networks; Optimization methods (N. Le Roux)

 PDF
10
 Nov 30
 Category-level localization; Face detection and recognition (C. Schmid)

Assignment 4 due. 		PPT1 PPT2 PDF1 PDF2
11
 Dec 7
 Scenes and objects (I. Laptev, J. Sivic)

 PDF1 PDF2
12 Dec 14 Final project presentations and evaluation (I. Laptev, J. Sivic)

Project reports due date extended to January 5th 2011 


Relevant literature: