Head pose estimation in the wild using Convolutional Neural Networks and adaptive gradient methods
- Submitting institution
-
University of Plymouth
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 902
- Type
- D - Journal article
- DOI
-
10.1016/j.patcog.2017.06.009
- Title of journal
- Pattern Recognition
- Article number
- -
- First page
- 132
- Volume
- 71
- Issue
- -
- ISSN
- 0031-3203
- Open access status
- Compliant
- Month of publication
- June
- Year of publication
- 2017
- 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
- 70
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This pioneering work on head-pose estimation "in the wild" domain has led to the establishment of a large number of deep learning projects. This is evidenced by the high citations of papers on extended head-pose recognition and the GitHub metrics (1100 stars&350 forks). The model is important because it is utilised in various car driver attention systems (e.g. "AutoRate" by Microsoft Research), and IoT-systems for object-detection, gaze-estimation and social group interaction (in labs in Daejeon, Dankook and Kumoh). This work, funded by the US project "THRIVE" on trust in human-robot interaction, led to the 5-year follow-up follow-up THRIVE++ project (2019-2024).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -