DMCA
Hierarchical Saliency Detection
| Citations: | 33 - 3 self |
BibTeX
@MISC{Yan_hierarchicalsaliency,
author = {Qiong Yan and Li Xu and Jianping Shi and Jiaya Jia},
title = {Hierarchical Saliency Detection},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
When dealing with objects with complex structures, saliency detection confronts a critical problem – namely that detection accuracy could be adversely affected if salient foreground or background in an image contains small-scale high-contrast patterns. This issue is common in natural images and forms a fundamental challenge for prior methods. We tackle it from a scale point of view and propose a multi-layer approach to analyze saliency cues. The final saliency map is produced in a hierarchical model. Different from varying patch sizes or downsizing images, our scale-based region handling is by finding saliency values optimally in a tree model. Our approach improves saliency detection on many images that cannot be handled well traditionally. A new dataset is also constructed. 1.
Keyphrases
hierarchical saliency detection saliency detection saliency value complex structure many image new dataset critical problem final saliency map detection accuracy patch size natural image hierarchical model saliency cue small-scale high-contrast pattern scale-based region handling scale point salient foreground prior method multi-layer approach fundamental challenge tree model
