A Unified Deep Metric Representation for Mesh Saliency Detection and Non-rigid Shape Matching
- Submitting institution
-
University of Northumbria at Newcastle
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 27499588
- Type
- D - Journal article
- DOI
-
10.1109/tmm.2019.2952983
- Title of journal
- IEEE Transactions on Multimedia
- Article number
- 8896033
- First page
- 2278
- Volume
- 22
- Issue
- 9
- ISSN
- 1520-9210
- Open access status
- Compliant
- Month of publication
- November
- 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
-
4
- Research group(s)
-
D - Computer Vision and Natural Computing (CVNC)
- Citation count
- 0
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper opened the idea of jointly solving salient points detection and matching across 3D surface meshes for mutual benefits using deep learning. It was for the first time validated that saliency detection and shape matching are more accurate under non-isometric shape deformations with the help of each other. All software codes were open-sourced to advance future research at http://hubertshum.com/info/tmm2020.htm. The work was an international collaboration between the UK (Northumbria University, Durham University) and China (Beihang University).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -