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
Actions
Access Document
- Files:
-
-
(Accepted manuscript, pdf, 211.6KB)
-
- Publisher copy:
- 10.1109/ICIP.2016.7533204
Authors
Bibliographic Details
- Publisher:
- IEEE Publisher's website
- Journal:
- 2016 IEEE International Conference on Image Processing (ICIP) Journal website
- Pages:
- 4463-4467
- Host title:
- 2016 IEEE International Conference on Image Processing (ICIP)
- Publication date:
- 2016-08-19
- Acceptance date:
- 2016-05-13
- DOI:
- ISSN:
-
2381-8549
- Source identifiers:
-
811333
- ISBN:
- 9781467399616
Item Description
- Keywords:
- Pubs id:
-
pubs:811333
- UUID:
-
uuid:8ae741b2-4dc2-49c5-83e2-ac8e2224c0ec
- Local pid:
- pubs:811333
- Deposit date:
- 2017-12-15
Terms of use
- Copyright holder:
- IEEE
- Copyright date:
- 2016
- Notes:
- Copyright © 2016 IEEE. This is the accepted manuscript version of the paper. The final version is available online from IEEE at: https://doi.org/10.1109/ICIP.2016.7533204
If you are the owner of this record, you can report an update to it here: Report update to this record