Conference item icon

Conference item

Truncated max-of-convex models

Abstract:

Truncated convex models (TCM) are a special case of pairwise random fields that have been widely used in computer vision. However, by restricting the order of the potentials to be at most two, they fail to capture useful image statistics. We propose a natural generalization of TCM to high-order random fields, which we call truncated maxof- convex models (TMCM). The energy function of TMCM consists of two types of potentials: (i) unary potential, which has no restriction on its form; and (ii) ...

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

Actions


Access Document


Files:
Publisher copy:
10.1109/CVPR.2017.78

Authors


More by this author
Institution:
University of Oxford
Oxford college:
Lady Margaret Hall
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
Google DeepMind More from this funder
Publisher:
Institute of Electronics and Electrical Engineers Publisher's website
Journal:
Conference on Computer Vision and Pattern Recognition (CVPR 2017) Journal website
Host title:
Conference on Computer Vision and Pattern Recognition (CVPR 2017)
Publication date:
2017-11-01
Acceptance date:
2017-03-03
DOI:
Source identifiers:
708414
Pubs id:
pubs:708414
UUID:
uuid:b0e9b6bf-d3da-42ca-9191-f258e6c42649
Local pid:
pubs:708414
Deposit date:
2017-07-18

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