Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/99020
Title: Removing label ambiguity in learning-based visual saliency estimation
Authors: Li, Jia
Xu, Dong
Gao, Wen
Keywords: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
Issue Date: 2011
Source: Li, J., Xu, D., & Gao, W. (2011). Removing label ambiguity in learning-based visual saliency estimation. IEEE transactions on image processing, 21(4), 1513-1525.
Series/Report no.: IEEE transactions on image processing
Abstract: Visual saliency is a useful clue to depict visually important image/video contents in many multimedia applications. In visual saliency estimation, a feasible solution is to learn a “feature-saliency” mapping model from the user data obtained by manually labeling activities or eye-tracking devices. However, label ambiguities may also arise due to the inaccurate and inadequate user data. To process the noisy training data, we propose a multi-instance learning to rank approach for visual saliency estimation. In our approach, the correlations between various image patches are incorporated into an ordinal regression framework. By iteratively refining a ranking model and relabeling the image patches with respect to their mutual correlations, the label ambiguities can be effectively removed from the training data. Consequently, visual saliency can be effectively estimated by the ranking model, which can pop out real targets and suppress real distractors. Extensive experiments on two public image data sets show that our approach outperforms 11 state-of-the-art methods remarkably in visual saliency estimation.
URI: https://hdl.handle.net/10356/99020
http://hdl.handle.net/10220/13473
ISSN: 1057-7149
DOI: http://dx.doi.org/10.1109/TIP.2011.2179665
Rights: © 2011 IEEE
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:SCSE Journal Articles

Google ScholarTM

Check

Altmetric

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.