Robust Correlated and Individual Component Analysis
- Submitting institution
-
Goldsmiths' College
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2011
- Type
- D - Journal article
- DOI
-
10.1109/TPAMI.2015.2497700
- Title of journal
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Article number
- -
- First page
- 1665
- Volume
- 38
- Issue
- 8
- ISSN
- 0162-8828
- Open access status
- Out of scope for open access requirements
- Month of publication
- August
- Year of publication
- 2015
- URL
-
http://research.gold.ac.uk/id/eprint/17321/
- 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
-
3
- Research group(s)
-
-
- Citation count
- 23
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- In this work, the first robust component analysis framework suitable for handling data with non-Gaussian corruptions and temporal incongruities, which is a common scenario when learning from data captured under real-world conditions. The method has been utilized for robust fusion of audio-visual data under real-world settings, and state-of-the-art results have been presented in problems such as heterogeneous face recognition, subspace clustering, and the prediction of social signals (interest, conflict). This work has been paramount to the success of EU funded projects such as TERESA (FP7/2013-2016) and SEWA (H2020/2014-2020). It has been presented in a top conference in the field (CVPR).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -