Contextualizing object detection and classification
- Submitting institution
-
Queen's University of Belfast
- Unit of assessment
- 12 - Engineering
- Output identifier
- 136525534
- Type
- D - Journal article
- DOI
-
10.1109/TPAMI.2014.2343217
- Title of journal
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Article number
- -
- First page
- 13
- Volume
- 37
- Issue
- 1
- ISSN
- 0162-8828
- Open access status
- Out of scope for open access requirements
- Month of publication
- July
- Year of publication
- 2014
- 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
-
5
- Research group(s)
-
C - Electrical and Electronic
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper proposes a new method for adaptive context modelling and iterative performance boosting, which aims to solve the fundamental problems (i.e. visual object classification and detection) in the field of computer vision. The first Context-SVM algorithm with an iterative training procedure is presented and achieves the state-of-the-art results. The work won the prestigious international competition - PASCAL VOC Challenge Classification Competition - in 2010, 2011 and 2012 consecutively, led the award of a US patent (8,687,851) and was integrated into a photo-management product launched in Japan by Panasonic.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -