event thumbnail image
OPEN HOUSE on Multi-Task and Complex Outputs Learning
Pascal

Learning shared representations for object recognition

author: Antonio Torralba, MIT - Massachusetts Institute of Technology
You might be experiencing some problems with Your Video player.
Slides
0:01 Learning shared representations for object recognition
0:19 Collaborators
0:37 Standard approach for object detection
1:53 Face detection
2:17 The single class age
2:35 Multiclass object detection
3:10 Object detection and the “Head in the coffee beans problem”
3:14 “Head in the coffee beans problem”
3:33 “Head in the coffee beans problem”
4:27 Symptoms of local detectors
5:27 Failure modes for object presence detection
6:13 The system does not care about the scene, but we do…
6:38 Some symptoms of one-vs-all multiclass approaches
7:49 Some symptoms of one-vs-all multiclass approaches
8:19 Some symptoms of one-vs-all multiclass approaches
8:47 Green pastures for research in multiclass object detection

Lecture rating

People found this lecture:
Worth seeing
because it is:
 Valuable and informative
Well presented
Easily understandable
Acceptably recorded
You need to login to cast your vote.

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.

Link this page

Would you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !

Reviews and comments:

Comment1 Gustavo Manzanilla, July 1, 2008 at 3:24 p.m.:

Interesting advanced in the recognition of images, less pixels, more cheap. Keep going, and it will be better.


Write your own review or comment: