Aff-Wild: Valence and Arousal ‘in-the-wild’ Challenge
- Submitting institution
-
Middlesex University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1222
- Type
- E - Conference contribution
- DOI
-
10.1109/CVPRW.2017.248
- Title of conference / published proceedings
- 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
- First page
- 1980
- Volume
- -
- Issue
- -
- ISSN
- 2160-7516
- Open access status
- Compliant
- Month of publication
- July
- Year of publication
- 2017
- URL
-
http://eprints.mdx.ac.uk/22045/
- 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
-
5
- Research group(s)
-
-
- Citation count
- 8
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Behavioural modelling and analysis constitute a crucial aspect of Human Computer Interaction when it comes to recognising human emotions based on facial expression. This paper is significant because it proposes a new comprehensive benchmark for assessing the performance of facial affect, behaviour analysis, and understanding ‘in-the-wild’ by detailing the Affect-in-the-Wild Challenge. It presents the database description, the experimental set up, the baseline method used for the Challenge and finally the summary of the performance of the different methods submitted to the Challenge for Valence and Arousal estimation, demonstrating very good performance when trained with in-the-wild data.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -