Discriminative shared Gaussian processes for multiview and view-invariant facial expression recognition
- Submitting institution
-
Imperial College of Science, Technology and Medicine
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2174
- Type
- D - Journal article
- DOI
-
10.1109/TIP.2014.2375634
- Title of journal
- IEEE Transactions on Image Processing
- Article number
- -
- First page
- 189
- Volume
- 24
- Issue
- 1
- ISSN
- 1057-7149
- Open access status
- Out of scope for open access requirements
- Month of publication
- November
- Year of publication
- 2014
- URL
-
-
- Supplementary information
-
10.1109/TIP.2014.2375634
- 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
-
2
- Research group(s)
-
-
- Citation count
- 127
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The paper introduces a novel Gaussian process-based latent variable model for automatic facial expression analysis, using multi view and view-invariant classification of facial expressions. It underpins the EC H2020 SEWA grant (https://sewaproject.eu, £2.5M), as well as Pantic’s appointment as a Scientific Advisor to RealEyes from April 2015 (https://www.realeyesit.com). RealEyes uses face analysis to analyse people's reactions to adverts from videos recorded in the wild (with various facial views). Led to keynote invitations at ECMR'15 (https://lcas.lincoln.ac.uk/ecmr-usb/media/invited.html) and ACPR’15 (http://acpr2015.org/programme/iapr-invited-speakers/).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
