Incremental face alignment in the wild
- Submitting institution
-
Imperial College of Science, Technology and Medicine
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2222
- Type
- E - Conference contribution
- DOI
-
10.1109/CVPR.2014.240
- Title of conference / published proceedings
- Proceedings of IEEE Int'l Conf. on Computer Vision & Pattern Recognition (CVPR 2014)
- First page
- 1859
- Volume
- -
- Issue
- 1
- ISSN
- 1063-6919
- Open access status
- Out of scope for open access requirements
- Month of publication
- September
- Year of publication
- 2014
- URL
-
-
- Supplementary information
-
10.1109/CVPR.2014.240
- 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
-
3
- Research group(s)
-
-
- Citation count
- 211
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The paper presents one of the first incremental learning methodologies for cascade regression, the method of choice for facial landmark localisation and tracking at that time. The method outperformed the state-of-the-art in facial landmark tracking by a large margin. The paper was the basis of the EPSRC project "ADAManT: Adaptive Facial Deformable Models for Tracking" (EP/L026813/1; £100K). The software of the method has been exclusively licensed to Seeing Machines for driver monitoring (https://www.seeingmachines.com).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
