Estimation of quality scores from subjective tests : beyond subjects' MOS
- Submitting institution
-
Kingston University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11-11-1345
- Type
- D - Journal article
- DOI
-
10.1109/TMM.2020.3013349
- Title of journal
- IEEE Transactions on Multimedia
- Article number
- -
- First page
- 0
- Volume
- 0
- Issue
- -
- ISSN
- 1520-9210
- Open access status
- Compliant
- Month of publication
- -
- Year of publication
- 2020
- 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
-
-
- Research group(s)
-
-
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Quality assessment via subjective tests is typically performed by taking the mean value of the opinion scores of the subjects taking part in the evaluation (sample mean). The model proposed here estimates the “population mean” based on the “sample mean”. This value, supported by rigorous statistics, gives a better indication of the quality. This work, and its publicly available implementation, has the potential to impact highly the scientific and industrial communities on multimedia communications. Indeed, industries, e.g., Netflix, are seeking better ways to assess the quality based on subjective tests, considering the impact of the type of the involved subjects.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -