Conference item icon

Conference item

Co-attention for conditioned image matching

Abstract:

We propose a new approach to determine correspondences between image pairs in the wild under large changes in illumination, viewpoint, context, and material. While other approaches find correspondences between pairs of images by treating the images independently, we instead condition on both images to implicitly take account of the differences between them. To achieve this, we introduce (i) a spatial attention mechanism (a co-attention module, CoAM) for conditioning the learned features on bo...

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

Actions


Access Document


Files:
Publisher copy:
10.1109/CVPR46437.2021.01566

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:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Oxford college:
Brasenose College
Role:
Author
ORCID:
0000-0002-8945-8573
Publisher:
Institute of Electrical and Electronics Engineers Publisher's website
Pages:
15915-15924
Host title:
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publication date:
2021-11-13
Acceptance date:
2021-02-28
Event title:
Conference on Computer Vision and Pattern Recognition (CVPR 2021)
Event location:
Virtual event
Event website:
http://cvpr2021.thecvf.com/
Event start date:
2021-06-19T00:00:00Z
Event end date:
2021-06-25T00:00:00Z
DOI:
EISBN:
9781665445092
EISSN:
2575-7075
ISSN:
1063-6919
ISBN:
9781665445108
Language:
English
Keywords:
Pubs id:
1173940
Local pid:
pubs:1173940
Deposit date:
2021-04-28

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