Conference item icon

Conference item : Conference-proceeding

Straight to Shapes: Real-time Detection of Encoded Shapes

Abstract:

Current object detection approaches predict bounding boxes that provide little instance-specific information beyond location, scale and aspect ratio. In this work, we propose to regress directly to objects’ shapes in addition to their bounding boxes and categories. It is crucial to find an appropriate shape representation that is compact and decodable, and in which objects can be compared for higher order concepts such as view similarity, pose variation and occlusion. To achieve this, we use ...

Expand abstract

Actions


Access Document


Files:
  • (Accepted manuscript, pdf, 5.1MB)
Publisher copy:
10.1109/CVPR.2017.448

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 by this author
Institution:
University of Oxford
Oxford college:
Wolfson College
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
More from this funder
Grant:
Seebibyte EP/M013774/1, EPSRC/MURI EP/N019474/1
More from this funder
Grant:
ERC-2012-AdG 321162-HELIOS
Publisher:
Institute of Electrical and Electronics Engineers Publisher's website
Journal:
CVPR 2017: IEEE Conference on Computer Vision and Pattern Recognition Journal website
Host title:
CVPR 2017: IEEE Conference on Computer Vision and Pattern Recognition
Publication date:
2017-11-09
Acceptance date:
2017-03-18
DOI:
Source identifiers:
689003
ISBN:
9781538604571
Subtype:
conference-proceeding
Pubs id:
pubs:689003
UUID:
uuid:1e312239-8533-4670-a2f6-ca1b4b1082f6
Local pid:
pubs:689003
Deposit date:
2017-04-11

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