Conference item icon

Conference item

Learning human poses from actions

Abstract:

We consider the task of learning to estimate human pose in still images. In order to avoid the high cost of full supervision, we propose to use a diverse data set, which consists of two types of annotations: (i) a small number of images are labeled using the expensive ground-truth pose; and (ii) other images are labeled using the inexpensive action label. As action information helps narrow down the pose of a human, we argue that this approach can help reduce the cost of training without signi...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed
Version:
Accepted Manuscript

Actions


Access Document


Files:

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Oxford college:
Lady Margaret Hall
Role:
Author
Publisher:
British Machine Vision Association Publisher's website
Publication date:
2018-09-03
Acceptance date:
2018-07-02
Pubs id:
pubs:891168
URN:
uri:6587d7e8-edac-43ea-ad63-981aef2fd196
UUID:
uuid:6587d7e8-edac-43ea-ad63-981aef2fd196
Local pid:
pubs:891168

Terms of use


Metrics


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