Reconnaissance d’objets et vision artificielle 2011/2012

Object recognition and computer vision 2011/2012


Jean Ponce, Ivan Laptev, Cordelia Schmid and Josef Sivic



Course Information

Room: ENS Ulm  Salle UV aile Rataud, 45 rue d'Ulm
Class time: Tuesday 16:15-19:15

News:

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 three programming assignments representing 60% of the grade.

1. Stitching photo mosaics.  Hand out date: 3/10/2011. Due date: 18/10/2011.
2. Bag-of-features image classification. Hand out date: 18/10/2011. Due date: 8/11/2011.
3. Simple face detector.

Final project

The final project will represent 40% of the grade.

Topic suggestions for the final project are here. 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).  

Matlab tutorial

The supporting materials for the programming assignments and final project will be in Matlab. 
There will be a Matlab tutorial for beginners on Friday 30/11/2011 at 10:30-12:00. The tutorial will be at 23 avenue d'Italie - Salle Rose.
Materials from the tutorial are here.

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.

List of received reports

https://docs.google.com/spreadsheet/pub?key=0Aso5oi2c4UB5dGVXXzFIRWZoZ24wNzNuQll5c3FsNXc&output=html


Course schedule (subject to change)

Lecture
 Date
 		Topic and reading materials.
 		Slides
1
 Sep 27
 Introduction (J. Ponce);  Instance-level recognition I. - Camera geometry (J. Sivic);

History: J. Mundy - Object recognition in the geometric era: A retrospective.
Camera geometry: Forsyth&Ponce Ch.1-2. Hartley&Zisserman - Ch.6
 PPT1 PPT2 PDF1 PDF2
Matlab tutorial scripts
2
 Oct 4
 Instance-level recognition II. - Local invariant features (C. Schmid)

Mikolajczyk & Schmid, Scale and affine invariant interest point detectors, IJCV 2004
D. Lowe, Distinctive image features from scale-invariant keypoints, IJCV 2004
R. Szeliski (pdf), Sections 4.1, 4.1.1 and 4.1.2 from Chapter 4: Feature detection and matching.

Assignment 1 out. 		PDF1 PDF2
3
 Oct 11
 Instance-level recognition III. - Correspondence, efficient visual search (J. Sivic)

R. Szeliski (pdf), Sections 4.1.3 (feature matching) and 6.1 (feature-based alignment)
Muja & Lowe, Fast approx. nearest neighbors with automatic algorithm configuration, VISAPP'09
Sivic & Zisserman, Video Google: Efficient visual search of videos (chapter from this book)
Philbin et al., Object retrieval with large vocabularies and fast spatial matching, CVPR'07.

 PDF1 PDF2
4
 Oct 18
 Instance-level recognition IV. - Very large scale image indexing (C. Schmid)
Jegou et al., Improving bag-of-features for large scale image search, IJCV 2010
Jegou et al., Aggregating local image descriptors into compact codes, PAMI 2011

Bag-of-feature models for category-level recognition (C. Schmid)
Csurka et al., Visual categorization with bags of keypoints, 2004

Assignment 1 due. Assignment 2 out.  		PDF1 PDF2
5
 Oct 25
 Sparse coding and dictionary learning for image analysis (J. Ponce) 
Bach,Mairal,Ponce,Sapiro, Tutorial on sparse coding and dictionary learning for image analysis, at CVPR'10

Category-level localization I. (J. Sivic)
Fergus et al., A Sparse Object Category Model for Efficient Learning and Complete Recognition (chapter from this book)
Leibe et al., An Implicit Shape Model for Combined Object Categorization and Segmentation (chapter from this book)
Dalal&Triggs, A histogram of oriented gradients for human detection, CVPR'05

Topic suggestions for the final project are out. 		PDF1 PDF2
6 Nov 1
 (Holidays, no lecture.)
7 Nov 8
 Neural networks; Optimization methods (N. Le Roux)

Assignment 2 due. Final project proposal due. Assignment 3 out.  		PDF
8
 Nov 15
 Category-level localization II. - Efficient fitting of pictorial structures (J. Sivic / I. Laptev)
Human pose estimation (I. Laptev).
 

 PDF
9
 Nov 22
 Motion and human actions (I. Laptev)

Assignment 3 due. 		PDF
10
 Nov 29
 Face detection and recognition, segmentation (C. Schmid)

 		PDF1 PDF2 PDF3
11
 Dec 6
 Scenes and objects (I. Laptev, J. Sivic)

 PDF1 PDF2
12 Dec 9 
Dec 12 		Final project presentations and evaluation (I. Laptev, J. Sivic)
Note unusual time: Friday Dec 9 (14:00-17:00) / Monday Dec 12 (10:00-13:00)




Relevant literature: