Cosaliency Detection Based on Intrasaliency Prior Transfer and Deep Intersaliency Mining
- Submitting institution
-
Aberystwyth University / Prifysgol Aberystwyth
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 38986643
- Type
- D - Journal article
- DOI
-
10.1109/TNNLS.2015.2495161
- Title of journal
- IEEE Transactions on Neural Networks and Learning Systems
- Article number
- -
- First page
- 1163
- Volume
- 27
- Issue
- 6
- ISSN
- 2162-237X
- Open access status
- Out of scope for open access requirements
- Month of publication
- November
- Year of publication
- 2015
- 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
-
3
- Research group(s)
-
-
- Citation count
- 110
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work enables, for the first time, deep learning models to become applicable to co-saliency detection, concerning the task to detect common salient objects from multiple related images. It has led to a wide range of computer vision applications and has been regarded as one of the earliest baseline algorithms in the field of co-saliency detection (X Qian at U Texas), against which many follow-up studies carried out internationally compare. TNNLS is the premier journal in the area of neural nets and machine learning.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -