Conference item icon

Conference item

Knowing who to listen to: Prioritizing experts from a diverse ensemble for attribute personalization

Abstract:

Learning attribute models for applications like Zero-Shot Learning (ZSL) and image search is challenging because they require attribute classifiers to generalize to test data that may be very different from the training data. A typical scenario is when the notion of an attribute may differ from one user to another, e.g. one user may find a shoe formal whereas another user may not. In this case, the distribution of labels at test time is different from that at training time. We argue that due ...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed
Version:
Accepted Manuscript

Actions


Access Document


Files:
Publisher copy:
10.1109/ICIP.2016.7533204

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 Division
Department:
Engineering Science
Role:
Author
Publisher:
IEEE Publisher's website
Pages:
4463-4467
Publication date:
2016-08-19
Acceptance date:
2016-05-13
DOI:
ISSN:
2381-8549
Pubs id:
pubs:811333
URN:
uri:8ae741b2-4dc2-49c5-83e2-ac8e2224c0ec
UUID:
uuid:8ae741b2-4dc2-49c5-83e2-ac8e2224c0ec
Local pid:
pubs:811333
ISBN:
978-1-4673-9961-6

Terms of use


Metrics


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