Neural Information Processing Systems - NIPS05 Workshops

The Pyramid Match Kernel: Efficient Learning with Sets of Features

author: Kristen Grauman, University of Texas

Categories

Top: Computer Science: Machine Learning: Kernel Methods

You might be experiencing some problems with Your Video player.

*Slides*
0:00	The Pyramid Match Kernel: Efficient Learning with Sets of Features
0:12	Global (vector) representations
0:41	Real world challenges
0:58	Sets of local features
1:44	Sets of features in vision
2:34	Sets of features
3:13	Problem
3:35	Existing set kernels
5:02	Partial matching for sets of features
6:07	Pyramid match kernel
6:52	Pyramid match overview
7:54	Pyramid match kernel
8:14	Feature extraction
9:04	Counting matches
9:51	Counting new matches
10:21	Pyramid match kernel
11:07	Efficiency
11:36	Example pyramid match
11:55	Example pyramid match
12:05	Example pyramid match
12:12	Example pyramid match
12:30	Point sets with 5 to 100 points
13:06	Learning with the pyramid match
13:36	Object recognition results
14:19	Object recognition
15:29	Regression for pose
16:30	Regression for pose
17:06	Regression for pose
18:23	Regression for publication time
19:11	Regression for publication time
21:32	Summary
22:06	Future work

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.