Semantically tied paired cycle consistency for zero-shot sketch-based image retrieval
- Submitting institution
-
University of Exeter
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 6404
- Type
- E - Conference contribution
- DOI
-
10.1109/CVPR.2019.00523
- Title of conference / published proceedings
- Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
- First page
- 5084
- Volume
- 2019-June
- Issue
- -
- ISSN
- 1063-6919
- Open access status
- Deposit exception
- Month of publication
- June
- Year of publication
- 2019
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
1
- Research group(s)
-
-
- Citation count
- 7
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper focuses on retrieving images by drawing sketches that are not seen during the training phase. The demo implementing the technology was presented in the Mobile World Congress in the year of 2019. Funding came from the EU MSCA (665919) and the Alan Turing Institute and the Dstl (Turing/D028/1.0), where they become interested in adapting such low-shot learning techniques for recognising overhead imagery necessary in defence. Invited talks were given at the University of Amsterdam, The Netherlands and the University of Bristol, United Kingdom.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -