Conference item icon

Conference item

Deep learning for detecting multiple space-time action tubes in videos

Abstract:

In this work, we propose an approach to the spatiotemporal localisation (detection) and classification of multiple concurrent actions within temporally untrimmed videos. Our framework is composed of three stages. In stage 1, appearance and motion detection networks are employed to localise and score actions from colour images and optical flow. In stage 2, the appearance network detections are boosted by combining them with the motion detection scores, in proportion to their respective spatial...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed
Version:
Publisher's version

Actions


Access Document


Files:
Publisher copy:
10.5244/C.30.58

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Cuzzolin, F More by this author
More from this funder
Grant:
ERC-2012-AdG 321162-HELIOS
Publisher:
British Machine Vision Conference Publisher's website
Publication date:
2016-09-01
Acceptance date:
2016-07-16
DOI:
Pubs id:
pubs:815403
URN:
uri:dc2907e1-b5eb-4ce6-ae10-cce20e21dfd4
UUID:
uuid:dc2907e1-b5eb-4ce6-ae10-cce20e21dfd4
Local pid:
pubs:815403

Terms of use


Metrics



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

TO TOP