Classifying Visual Scenes with Affine Invariant Regions and Text Retrieval Methods

author: Daniel Gatica-Perez, IDIAP Research Institute

You might be experiencing some problems with Your Video player.

*Slides*
0:00	Pump-priming: Modeling scenes with invariant regions and aspect models
0:19	Project details
0:55	The original goal: Scene classification
1:53	The final story
2:13	The bag of visterms (Sivic ’03, Willamowski ’04)
3:18	The bag of visterms (BOV)
3:43	Visterms as words
4:23	PLSA
4:57	Images as mixtures of aspects
5:13	Aspect-based image ranking (soft clustering)
5:38	Aspect representation
6:29	Aspect 4, city
6:50	Aspect 3, landscape
7:10	Aspect 6, landscape
7:32	Some experiments
8:13	Classification error
9:08	Some experiments
9:25	Classification error
9:50	Aspect-based «segmentation»
10:26	Aspect-based segmentation - 1
10:55	Aspect-based segmentation - 2
11:06	So, pump-priming?
11:19	Pump-priming, good timing
12:05	Scholar (snapshot)
12:27	Extensions
13:25	Conclusion

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.