Dynamic behavior analysis via structured rank minimization
- Submitting institution
-
Middlesex University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 775
- Type
- D - Journal article
- DOI
-
10.1007/s11263-016-0985-3
- Title of journal
- International Journal of Computer Vision
- Article number
- -
- First page
- 333
- Volume
- 126
- Issue
- 2-4
- ISSN
- 0920-5691
- Open access status
- Compliant
- Month of publication
- January
- Year of publication
- 2017
- URL
-
http://eprints.mdx.ac.uk/23768/
- 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
- 6
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Human behaviour and affect are inherently a dynamic phenomenon involving temporal evolution of patterns manifested through a multiplicity of non-verbal behavioural cues including facial expressions, body postures and gestures, and vocal outbursts. The paper is significant because it introduces a novel structured rank minimization method and its scalable variant. The new method outperforms other state-of-the-art methods based on the tasks of (i) conflict intensity prediction, (ii) prediction of valence and arousal, and (iii) tracklet matching. The approach is robust and effective.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -