Personalizing Human Video Pose Estimation
- Submitting institution
-
The University of Leeds
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- UOA11-665
- Type
- E - Conference contribution
- DOI
-
10.1109/CVPR.2016.334
- Title of conference / published proceedings
- 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- First page
- 3063
- Volume
- -
- Issue
- -
- ISSN
- 1063-6919
- Open access status
- Out of scope for open access requirements
- Month of publication
- December
- Year of publication
- 2016
- 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
-
4
- Research group(s)
-
B - AI (Artificial Intelligence)
- Citation count
- 15
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- An important way to improve performance in human pose estimation is to adapt automatically to the uniqueness of a person’s appearance.
The paper proposes a new way to do this, extrapolating from a small number of reliable estimates to obtain additional estimates used in adaptation. The method outperforms the state of the art by a large margin on two standard benchmarks, as well as on a new challenging YouTube video dataset. Accepted for oral presentation (one of less than 4% of 2145 submissions). There were over 3500 delegates at the conference.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
