Vide-omics : a genomics-inspired paradigm for video analysis
- Submitting institution
-
Kingston University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11-44-1329
- Type
- D - Journal article
- DOI
-
10.1016/j.cviu.2017.10.003
- Title of journal
- Computer Vision and Image Understanding
- Article number
- -
- First page
- 28
- Volume
- 166
- Issue
- -
- ISSN
- 1077-3142
- Open access status
- Compliant
- Month of publication
- -
- 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
-
-
- Research group(s)
-
-
- Citation count
- 2
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper introduced a novel paradigm for video analysis. Based on the principles of genomics, it is designed to handle the large variability encountered in real-life visual surveillance data. Experiments conducted on videos captured by free-moving cameras demonstrate its robustness. This paradigm could impact significantly the computer vision community: a popular science article reporting this work –‘DNA techniques could transform facial recognition technology’ - attracted over 23,000 readers and was republished by ‘Scientific American’; moreover, the lead academic was invited to write a 3-page article on the topic in Elsevier’s business newsletter ‘Biometric Technology Today’, published in March 2018.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -