The research of detecting co-saliency over multiple images is just beginning. The existing methods multiply the saliency on single image by the correspondence over multiple images to estimate co-saliency. They have difficulty in highlighting the co-salient object that is not salient on single image. It is caused by two problems. (1) The correspondence computation lacks precision. (2) The co-saliency multiplication formulation does not fully consider the effect of correspondence for co-saliency. In this paper, we propose a novel co-saliency detection scheme linearly combining foreground correspondence and single-view saliency. The progressive graph matching based foreground correspondence method is proposed to improve the precision of correspondence computation. Then the foreground correspondence is linearly combined with single-view saliency to compute co-saliency. According to the linear combination formulation, high correspondence could bring about high co-saliency, even when single-view saliency is low. Experiments show that our method outperforms previous state-of-the-art co-saliency methods.
Huiyun JING
China Academy of Telecommunication Research of MIIT
Xin HE
Coordination Center of China
Qi HAN
Harbin Institute of Technology
Xiamu NIU
Harbin Institute of Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Huiyun JING, Xin HE, Qi HAN, Xiamu NIU, "Co-saliency Detection Linearly Combining Single-View Saliency and Foreground Correspondence" in IEICE TRANSACTIONS on Information,
vol. E98-D, no. 4, pp. 985-988, April 2015, doi: 10.1587/transinf.2014EDL8172.
Abstract: The research of detecting co-saliency over multiple images is just beginning. The existing methods multiply the saliency on single image by the correspondence over multiple images to estimate co-saliency. They have difficulty in highlighting the co-salient object that is not salient on single image. It is caused by two problems. (1) The correspondence computation lacks precision. (2) The co-saliency multiplication formulation does not fully consider the effect of correspondence for co-saliency. In this paper, we propose a novel co-saliency detection scheme linearly combining foreground correspondence and single-view saliency. The progressive graph matching based foreground correspondence method is proposed to improve the precision of correspondence computation. Then the foreground correspondence is linearly combined with single-view saliency to compute co-saliency. According to the linear combination formulation, high correspondence could bring about high co-saliency, even when single-view saliency is low. Experiments show that our method outperforms previous state-of-the-art co-saliency methods.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2014EDL8172/_p
Copy
@ARTICLE{e98-d_4_985,
author={Huiyun JING, Xin HE, Qi HAN, Xiamu NIU, },
journal={IEICE TRANSACTIONS on Information},
title={Co-saliency Detection Linearly Combining Single-View Saliency and Foreground Correspondence},
year={2015},
volume={E98-D},
number={4},
pages={985-988},
abstract={The research of detecting co-saliency over multiple images is just beginning. The existing methods multiply the saliency on single image by the correspondence over multiple images to estimate co-saliency. They have difficulty in highlighting the co-salient object that is not salient on single image. It is caused by two problems. (1) The correspondence computation lacks precision. (2) The co-saliency multiplication formulation does not fully consider the effect of correspondence for co-saliency. In this paper, we propose a novel co-saliency detection scheme linearly combining foreground correspondence and single-view saliency. The progressive graph matching based foreground correspondence method is proposed to improve the precision of correspondence computation. Then the foreground correspondence is linearly combined with single-view saliency to compute co-saliency. According to the linear combination formulation, high correspondence could bring about high co-saliency, even when single-view saliency is low. Experiments show that our method outperforms previous state-of-the-art co-saliency methods.},
keywords={},
doi={10.1587/transinf.2014EDL8172},
ISSN={1745-1361},
month={April},}
Copy
TY - JOUR
TI - Co-saliency Detection Linearly Combining Single-View Saliency and Foreground Correspondence
T2 - IEICE TRANSACTIONS on Information
SP - 985
EP - 988
AU - Huiyun JING
AU - Xin HE
AU - Qi HAN
AU - Xiamu NIU
PY - 2015
DO - 10.1587/transinf.2014EDL8172
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E98-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2015
AB - The research of detecting co-saliency over multiple images is just beginning. The existing methods multiply the saliency on single image by the correspondence over multiple images to estimate co-saliency. They have difficulty in highlighting the co-salient object that is not salient on single image. It is caused by two problems. (1) The correspondence computation lacks precision. (2) The co-saliency multiplication formulation does not fully consider the effect of correspondence for co-saliency. In this paper, we propose a novel co-saliency detection scheme linearly combining foreground correspondence and single-view saliency. The progressive graph matching based foreground correspondence method is proposed to improve the precision of correspondence computation. Then the foreground correspondence is linearly combined with single-view saliency to compute co-saliency. According to the linear combination formulation, high correspondence could bring about high co-saliency, even when single-view saliency is low. Experiments show that our method outperforms previous state-of-the-art co-saliency methods.
ER -