A spatial-temporal framework based on histogram of gradients and optical flow for facial expression recognition in video sequences
- Submitting institution
-
The University of Warwick
- Unit of assessment
- 12 - Engineering
- Output identifier
- 8656
- Type
- D - Journal article
- DOI
-
10.1016/j.patcog.2015.04.025
- Title of journal
- Pattern Recognition
- Article number
- -
- First page
- 3407
- Volume
- 48
- Issue
- 11
- ISSN
- 0031-3203
- Open access status
- Out of scope for open access requirements
- Month of publication
- November
- Year of publication
- 2015
- 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
-
1
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper introduced PHOG-TOP (a 3D descriptor for representing faces and movement of facial landmarks) for a facial expression recognition framework that also exploits optical flow. The framework outperformed two state-of-the-art facial expression recognition methods. It led to an improved framework published in the same journal (doi:10.1016/j.patcog.2016.12.002). It helped the co-author to secure a research fellowship at Hong Kong Baptist University; resulted in an invited presentation at 2018 Multidisciplinary Symposium on Physiognomics (https://warwick.ac.uk/fac/cross_fac/ias/news/events/readingthebody/); and secured a collaborative research grant of £90,000 from Hong Kong Research Grants Council (Project number: 11202319) on micro facial expressions.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -