The UoS LAVA group Approach to Generic Image Categorisation

author: Jason Farquhar, Max Planck Institute for Biological Cybernetics

Categories

Top: Computer Science: Image Analysis
Top: Computer Science: Computer Vision

You might be experiencing some problems with Your Video player.

*Slides*
0:04	The UoS LAVA group Approach to Generic Image Categoristion
1:24	The ?set-of-patches? approach to image categorisation.
1:36	The ?set-of-patches? approach to image categorisation.
1:45	The ?set-of-patches? approach to image categorisation.
1:48	The ?set-of-patches? approach to image categorisation.
1:54	The ?set-of-patches? approach to image categorisation.
1:59	Image Processing
2:09	Image Processing
2:16	Image Processing
2:26	The ?set-of-patches? approach to image categorisation.
2:29	Feature Selection
2:48	Feature Selection
2:52	Feature Selection
3:08	Feature Selection
3:13	Feature Selection(2)
3:27	Feature Selection(2)
3:39	Feature Selection(4)? Partial Least Squares (PLS)
4:09	Feature Selection(5)
4:13	The ?set-of-patches? approach to image categorisation.
4:19	Kernel Computation
4:30	Kernel Computation
4:38	Kernel Computation(2) ? Set ! description mapping
4:51	Kernel Computation(2) ? Set ! description mapping
5:18	Kernel Computation(3) ? PDF Kernels
5:29	Kernel Computation(3) ? PDF Kernels
5:44	The ?set-of-patches? approach to image categorisation.
5:48	Classier Learning
6:25	Classier Learning
6:39	Classier Learning(2) ? SVM_2K
7:06	Classier Learning(3) ? SVM_2K
7:29	Results ? VOC test1 EER
7:58	Results ? VOC test1 EER
8:31	Conclusions & Further work
8:39	Conclusions & Further work
8:44	Conclusions & Further 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.