Conference item icon

Conference item

Integrator Perception with Recurrent Multi-Task Neural Networks

Abstract:

Modern discriminative predictors have been shown to match natural intelligences in specific perceptual tasks in image classification, object and part detection, boundary extraction, etc. However, a major advantage that natural intelligences still have is that they work well for all perceptual problems together, solving them efficiently and coherently in an integrated manner. In order to capture some of these advantages in machine perception, we ask two questions: whether deep neural networks ...

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

Actions


Access Document


Files:

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
More from this funder
Grant:
StartingGrant:Integrated
DetailedImageUnderst
ing(EP/L024683/1
Publisher:
Neural Information Processing Systems Foundation Publisher's website
Journal:
Neural Information Processing Systems 29th Annual Conference Journal website
Host title:
NIPS 2016: 29th Annual Conference on Neural Information Processing Systems
Publication date:
2016-12-01
Acceptance date:
2016-08-12
Source identifiers:
656024
Pubs id:
pubs:656024
UUID:
uuid:eacb854e-4bee-4a3e-95e7-1ff88417ca21
Local pid:
pubs:656024
Deposit date:
2016-11-01

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