Paper Info
Title
Salient Object Detection Using Window Mask Transferring With Multi-Layer Background Contrast
Abstract
In this paper, we present a novel framework to incorporate bottom-up features and top-down guidance to identify salient objects based on two ideas. The first one automatically encodes object location prior to predict visual saliency without the requirement of center-biased assumption, while the second one estimates image saliency using contrast with respect to background regions. The proposed framework consists of the following three basic steps: In the top-down process, we create a specific location saliency map (SLSM), which can be identified by a set of overlapping windows likely to cover salient objects. The binary segmentation masks of training windows are treated as high-level knowledge to be transferred to the test image windows, which may share visual similarity with training windows. In the bottom-up process, a multilayer segmentation framework is employed, which is able to provide vast robust background candidate regions specified by SLSM. Then the background contrast saliency map (BCSM) is computed based on low-level image stimuli features. SLSM and BCSM are finally integrated to a pixel-accurate saliency map. Extensive experiments show that our approach achieves the state-of-the-art results over MSRA 1000 and SED datasets.
Year
DOI
Venue
2014
10.1007/978-3-319-16811-1_15
COMPUTER VISION - ACCV 2014, PT III
Field
DocType
Volume
Computer vision,Saliency map,Multi layer,Salient object detection,Pattern recognition,Salience (neuroscience),Segmentation,Computer science,Salient objects,Artificial intelligence,Standard test image,Visual saliency
Conference
9005
ISSN
Citations 
PageRank 
0302-9743
1
0.35
References 
Authors
30
4
Name
Order
Citations
PageRank
Quan Zhou1565.31
Shu Cai229217.35
Shaojun Zhu385.95
Baoyu Zheng4100882.73