Action Recognition From Arbitrary Views Using Transferable Dictionary Learning
- Submitting institution
-
University of Northumbria at Newcastle
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 22062324
- Type
- D - Journal article
- DOI
-
10.1109/TIP.2018.2836323
- Title of journal
- IEEE Transactions on Image Processing
- Article number
- -
- First page
- 4709
- Volume
- 27
- Issue
- 10
- ISSN
- 1057-7149
- Open access status
- Compliant
- Month of publication
- May
- 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
-
3
- Research group(s)
-
D - Computer Vision and Natural Computing (CVNC)
- Citation count
- 18
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This novel transfer learning idea for recognizing human action recognition underpinned the award of Royal Society project “Modelling Human Motion for Synthesis and Recognition with Deep Learning on Surface Features” (IES\R2\181024) with Research Institute Computer and Systems Aléatoires (IRISA), a joint research centre with multiple French Institutes (Dr Antonio Mucherino, antonio.mucherino@irisa.fr). The action recognition aspect of this research led collaboration with Toyota Motor Europe (non-disclosure agreement signed with Yoshitaka Wakao, General Manager) for their humanoid robot development. It led to an invited talk at Waseda University, Japan (“Machine Learning for Human Motion Understanding” (invited by Shigeo Morishima, shigeo@waseda.jp).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
