Augmented Skeleton Space Transfer for Depth-based Hand Pose Estimation
- Submitting institution
-
The University of Bath
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 189106725
- Type
- E - Conference contribution
- DOI
-
10.1109/CVPR.2018.00869
- Title of conference / published proceedings
- 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
- First page
- 8330
- Volume
- -
- Issue
- -
- ISSN
- 2575-7075
- Open access status
- Compliant
- Month of publication
- December
- Year of publication
- 2018
- 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
-
2
- Research group(s)
-
-
- Citation count
- 9
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Human hand pose estimation techniques facilitate many practical applications, including augmented/virtual reality and video games. Existing work is limited in that they require a dataset covering diverse skeletal pose and camera views. This fundamental work overcomes this limitation by incorporating a novel technique that synthesizes new data entries during training and significantly broadened the application domain of hand pose analysis. Published in a top-tier venue, CVPR, this work spurred subsequent, influential efforts including RGB2Hands [Wang et al. SIGGRAPH Asia 2020].
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -