A combined convolutional neural network and potential region-of-interest model for saliency detection

Yu Hu; Zhen Liang; Zheru Chi; Hong Fu

doi:10.1109/ICNC.2015.7377982

A combined convolutional neural network and potential region-of-interest model for saliency detection

Yu Hu, Zhen Liang, Zheru Chi, Hong Fu

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

Abstract

A saliency detection model for approaching the human performance is a challenging research topic. In this paper, a new saliency model is proposed to detect saliency in natural scenes by using a trained convolutional neural network and a region-based validation method. The convolutional neural network (CNN) focuses on image details and local contrast of an image, while the region-based validation method focus on global information. Experimental results show that the two components of the model are complementary for each other in producing high-quality saliency maps.

Original language	English
Title of host publication	2015 11th International Conference on Natural Computation, ICNC 2015
Publisher	IEEE Computer Society
Pages	154-158
Number of pages	5
Volume	2016-January
ISBN (Electronic)	9781467376792
DOIs	https://doi.org/10.1109/ICNC.2015.7377982
Publication status	Published - 8 Jan 2016
Event	11th International Conference on Natural Computation, ICNC 2015 - Zhangjiajie, China Duration: 15 Aug 2015 → 17 Aug 2015

Conference

Conference	11th International Conference on Natural Computation, ICNC 2015
Country/Territory	China
City	Zhangjiajie
Period	15/08/15 → 17/08/15

Keywords

Convolutional neural networks
machine learning
saliency detection
saliency map

ASJC Scopus subject areas

Computer Science(all)
Biomedical Engineering
Computational Mechanics
Mathematics(all)
Neuroscience(all)

More information

10.1109/ICNC.2015.7377982

Cite this

@inproceedings{1b2a66e00ce0488f8d46b31e3e694630,

title = "A combined convolutional neural network and potential region-of-interest model for saliency detection",

abstract = "A saliency detection model for approaching the human performance is a challenging research topic. In this paper, a new saliency model is proposed to detect saliency in natural scenes by using a trained convolutional neural network and a region-based validation method. The convolutional neural network (CNN) focuses on image details and local contrast of an image, while the region-based validation method focus on global information. Experimental results show that the two components of the model are complementary for each other in producing high-quality saliency maps.",

keywords = "Convolutional neural networks, machine learning, saliency detection, saliency map",

author = "Yu Hu and Zhen Liang and Zheru Chi and Hong Fu",

year = "2016",

month = jan,

day = "8",

doi = "10.1109/ICNC.2015.7377982",

language = "English",

volume = "2016-January",

pages = "154--158",

booktitle = "2015 11th International Conference on Natural Computation, ICNC 2015",

publisher = "IEEE Computer Society",

address = "United States",

note = "11th International Conference on Natural Computation, ICNC 2015 ; Conference date: 15-08-2015 Through 17-08-2015",

}

Hu, Y, Liang, Z, Chi, Z & Fu, H 2016, A combined convolutional neural network and potential region-of-interest model for saliency detection. in 2015 11th International Conference on Natural Computation, ICNC 2015. vol. 2016-January, 7377982, IEEE Computer Society, pp. 154-158, 11th International Conference on Natural Computation, ICNC 2015, Zhangjiajie, China, 15/08/15. https://doi.org/10.1109/ICNC.2015.7377982

A combined convolutional neural network and potential region-of-interest model for saliency detection. / Hu, Yu; Liang, Zhen; Chi, Zheru; Fu, Hong.

2015 11th International Conference on Natural Computation, ICNC 2015. Vol. 2016-January IEEE Computer Society, 2016. p. 154-158 7377982.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - A combined convolutional neural network and potential region-of-interest model for saliency detection

AU - Hu, Yu

AU - Liang, Zhen

AU - Chi, Zheru

AU - Fu, Hong

PY - 2016/1/8

Y1 - 2016/1/8

N2 - A saliency detection model for approaching the human performance is a challenging research topic. In this paper, a new saliency model is proposed to detect saliency in natural scenes by using a trained convolutional neural network and a region-based validation method. The convolutional neural network (CNN) focuses on image details and local contrast of an image, while the region-based validation method focus on global information. Experimental results show that the two components of the model are complementary for each other in producing high-quality saliency maps.

AB - A saliency detection model for approaching the human performance is a challenging research topic. In this paper, a new saliency model is proposed to detect saliency in natural scenes by using a trained convolutional neural network and a region-based validation method. The convolutional neural network (CNN) focuses on image details and local contrast of an image, while the region-based validation method focus on global information. Experimental results show that the two components of the model are complementary for each other in producing high-quality saliency maps.

KW - Convolutional neural networks

KW - machine learning

KW - saliency detection

KW - saliency map

UR - http://www.scopus.com/inward/record.url?scp=84960457402&partnerID=8YFLogxK

U2 - 10.1109/ICNC.2015.7377982

DO - 10.1109/ICNC.2015.7377982

M3 - Conference article published in proceeding or book

VL - 2016-January

SP - 154

EP - 158

BT - 2015 11th International Conference on Natural Computation, ICNC 2015

PB - IEEE Computer Society

T2 - 11th International Conference on Natural Computation, ICNC 2015

Y2 - 15 August 2015 through 17 August 2015

ER -

A combined convolutional neural network and potential region-of-interest model for saliency detection

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Cite this