Unsupervised Attention-guided Image-to-Image Translation
- Submitting institution
-
The University of Bath
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 188557466
- Type
- E - Conference contribution
- DOI
-
-
- Title of conference / published proceedings
- Advances in Neural Information Processing Systems 31 (NIPS), 2018
- First page
- 1
- Volume
- -
- Issue
- -
- ISSN
- 1049-5258
- Open access status
- Compliant
- Month of publication
- December
- Year of publication
- 2018
- URL
-
https://papers.nips.cc/paper/2018/hash/4e87337f366f72daa424dae11df0538c-Abstract.html
- Supplementary information
-
https://papers.nips.cc/paper/7627-unsupervised-attention-guided-image-to-image-translation-supplemental.zip
- 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
-
4
- Research group(s)
-
-
- Citation count
- 1
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The ability to translate objects between images – e.g. transforming all horses into zebras – is a common task in image editing and manipulation. This paper proposes the first method to automatically achieve this task with no human input without altering the background. It does this by introducing the novel concept of attention mechanisms. The paper is highly influential – with over 100 citations since its publication at the end of 2018.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -