Conference item icon

Conference item

Future event prediction: If and when

Abstract:

We consider the problem of future event prediction in video: if and when a future event will occur. To this end, we propose a number of representations and loss functions tailored to this problem. These include several probabilistic formulations that also model the uncertainty of the prediction. We train and evaluate the approach on two entirely different prediction scenarios: if and when a car will stop in the BDD100k car driving dataset; and if and when a player is going to shoot a basketba...

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

Actions


Access Document


Files:
Publisher copy:
10.1109/CVPRW.2019.00354

Authors


More by this author
Institution:
University of Oxford
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Oxford college:
New College
Role:
Author
Publisher:
IEEE
Host title:
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Pages:
2935-2943
Publication date:
2020-07-11
Acceptance date:
2019-03-21
Event title:
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops
Event location:
Long Beach, CA, USA
Event website:
http://cvpr2019.thecvf.com/
Event start date:
2019-06-16
Event end date:
2019-06-17
DOI:
EISSN:
2160-7516
EISBN:
978-1-7281-2506-0
Language:
English
Keywords:
Pubs id:
pubs:1014931
UUID:
uuid:fca1a43d-1a60-4922-925f-7086d153f639
Local pid:
pubs:1014931
Source identifiers:
1014931
Deposit date:
2019-06-17

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