Conference item icon

Conference item

Self-supervised contrastive video-speech representation learning for ultrasound

Abstract:

In medical imaging, manual annotations can be expensive to acquire and sometimes infeasible to access, making conventional deep learning-based models difficult to scale. As a result, it would be beneficial if useful representations could be derived from raw data without the need for manual annotations. In this paper, we propose to address the problem of self-supervised representation learning with multi-modal ultrasound video-speech raw data. For this case, we assume that there is a high corr...

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

Actions


Access Document


Files:
Publisher copy:
10.1007/978-3-030-59716-0_51

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
ORCID:
0000-0003-0833-5115
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
ORCID:
0000-0002-2552-0964
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
Publisher:
Springer Publisher's website
Host title:
Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
Series:
Lecture Notes in Computer Science
Journal:
Lecture Notes in Computer Science Journal website
Volume:
12263
Pages:
534-543
Publication date:
2020-09-29
Event title:
MICCAI 2020: Medical Image Computing and Computer Assisted Intervention
Event location:
Germany
Event website:
https://www.miccai2020.org/en/
Event start date:
2020-10-04
Event end date:
2020-10-08
DOI:
EISSN:
1611-3349
ISSN:
0302-9743
Pmid:
33103162
ISBN:
9783030597153
Language:
English
Keywords:
Pubs id:
1139912
Local pid:
pubs:1139912
Deposit date:
2020-11-11

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