Journal article icon

Journal article

Learning view invariant recognition with partially occluded objects.

Abstract:

This paper investigates how a neural network model of the ventral visual pathway, VisNet, can form separate view invariant representations of a number of objects seen rotating together. In particular, in the current work one of the rotating objects is always partially occluded by the other objects present during training. A key challenge for the model is to link together the separate partial views of the occluded object into a single view invariant representation of that object. We show how t...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.3389/fncom.2012.00048

Authors


More by this author
Institution:
University of Oxford
Division:
MSD
Department:
Experimental Psychology
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MSD
Department:
Experimental Psychology
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MSD
Department:
Experimental Psychology
Role:
Author
More from this funder
Name:
Economic and Social Research Council
Funding agency for:
Tromans, J
Publisher:
Frontiers Media S.A.
Journal:
Frontiers in computational neuroscience More from this journal
Volume:
6
Issue:
JULY
Pages:
48
Publication date:
2012-01-01
DOI:
EISSN:
1662-5188
ISSN:
1662-5188
Language:
English
Keywords:
Pubs id:
pubs:344134
UUID:
uuid:f87abec0-161b-422f-9cec-7f9ba24d3486
Local pid:
pubs:344134
Source identifiers:
344134
Deposit date:
2012-12-19

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP