Arcface: additive angular margin loss for deep face recognition
- Submitting institution
-
Imperial College of Science, Technology and Medicine
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2165
- Type
- E - Conference contribution
- DOI
-
10.1109/CVPR.2019.00482
- Title of conference / published proceedings
- 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- First page
- 4685
- Volume
- 2019-June
- Issue
- -
- ISSN
- 2575-7075
- Open access status
- Compliant
- Month of publication
- January
- Year of publication
- 2020
- 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
-
3
- Research group(s)
-
-
- Citation count
- 198
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This is the only academically produced method that has entered the leaderboard of Face Recognition Vendor Test (FRVT), which is an independent evaluation of face recognition technology conducted by the US National Institute of Standards (https://www.nist.gov/programs-projects/frvt-11-verification). Currently, it is one of the top performing algorithms. CVPR 2019 oral presentation, acceptance rate: 5%/5160.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
