Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modeling
- Submitting institution
-
The University of Leeds
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- UOA11-3604
- Type
- D - Journal article
- DOI
-
10.1109/TVCG.2019.2936810
- Title of journal
- IEEE Transactions on Visualization and Computer Graphics
- Article number
- -
- First page
- 216
- Volume
- 27
- Issue
- 1
- ISSN
- 1077-2626
- Open access status
- Compliant
- Month of publication
- August
- Year of publication
- 2019
- 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)
-
D - CSE (Computational Science and Engineering)
- Citation count
- 1
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper proposed the first deep learning based approach to learn long-sequences of natural human motion manifold. Since publication in 2019, it has already inspired following research in several fields computer vision (DOI: 10.1109/CVPR42600), information science (DOI: 10.1109/ISPDS51347.2020.00016) and computer graphics(DOI: 10.1109/TVCG.2020.3028961). It has led to invitations to research talks in university (Durham), industry collaborations (Producer, Dubit Ltd; Director/Co-Founder, Prox and Reverie Ltd – names/contact details available on request), and research funding(~£300k, EP/R031193/1, EPSRC.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
