Conference item icon

Conference item

Few-shot action recognition with permutation-invariant attention

Abstract:

Many few-shot learning models focus on recognising images. In contrast, we tackle a challenging task of few-shot action recognition from videos. We build on a C3D encoder for spatio-temporal video blocks to capture short-range action patterns. Such encoded blocks are aggregated by permutation-invariant pooling to make our approach robust to varying action lengths and long-range temporal dependencies whose patterns are unlikely to repeat even in clips of the same class. Subsequently, the poole...

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

Actions


Access Document


Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Zoology
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
Expand authors...
Publisher:
Springer Publisher's website
Journal:
Proceedings of the European Conference on Computer Vision (ECCV 2020) Journal website
Volume:
12350
Pages:
525-542
Series:
Lecture Notes in Computer Science
Host title:
Proceedings of the European Conference on Computer Vision (ECCV 2020)
Publication date:
2020-10-29
Event title:
European Conference on Computer Vision (ECCV), 2020
Event location:
Online
Event website:
https://eccv2020.eu/
Event start date:
2020-08-23T00:00:00Z
Event end date:
2020-08-28T00:00:00Z
DOI:
EISBN:
978-3-030-58558-7
EISSN:
1611-3349
ISSN:
0302-9743
Pubs id:
1150997
Local pid:
pubs:1150997
ISBN:
9783030585570
Language:
English
Keywords:

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