Conference item icon

Conference item

Online real-time multiple spatiotemporal action localisation and prediction

Abstract:

We present a deep-learning framework for real-time multiple spatio-temporal (S/T) action localisation and classification. Current state-of-the-art approaches work offline, and are too slow to be useful in real-world settings. To overcome their limitations we introduce two major developments. Firstly, we adopt real-time SSD (Single Shot Multi-Box Detector) CNNs to regress and classify detection boxes in each video frame potentially containing an action of interest. Secondly, we design an origi...

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

Actions


Access Document


Files:
Publisher copy:
10.1109/ICCV.2017.393

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
More from this funder
Name:
Engineering & Physical Sciences Research Council
Grant:
EP/N019474/1
Publisher:
IEEE
Host title:
2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, Italy, 22-29 Oct. 2017
Journal:
IEEE International Conference on Computer Vision (ICCV) 2017 More from this journal
Publication date:
2017-12-25
Acceptance date:
2016-07-16
DOI:
ISBN:
9781538610329
Pubs id:
pubs:817299
UUID:
uuid:d2897e67-d872-4f44-a18c-10eeaeebe688
Local pid:
pubs:817299
Source identifiers:
817299
Deposit date:
2018-01-10

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