Saliency detection via absorbing Markov Chain

Bowen Jiang, Lihe Zhang, Huchuan Lu, Chuan Yang, Ming Hsuan Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

406 Citations (Scopus)

Abstract

In this paper, we formulate saliency detection via absorbing Markov chain on an image graph model. We jointly consider the appearance divergence and spatial distribution of salient objects and the background. The virtual boundary nodes are chosen as the absorbing nodes in a Markov chain and the absorbed time from each transient node to boundary absorbing nodes is computed. The absorbed time of transient node measures its global similarity with all absorbing nodes, and thus salient objects can be consistently separated from the background when the absorbed time is used as a metric. Since the time from transient node to absorbing nodes relies on the weights on the path and their spatial distance, the background region on the center of image may be salient. We further exploit the equilibrium distribution in an ergodic Markov chain to reduce the absorbed time in the long-range smooth background regions. Extensive experiments on four benchmark datasets demonstrate robustness and efficiency of the proposed method against the state-of-the-art methods.

Original languageEnglish
Title of host publicationProceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1665-1672
Number of pages8
ISBN (Print)9781479928392
DOIs
Publication statusPublished - 2013 Jan 1
Event2013 14th IEEE International Conference on Computer Vision, ICCV 2013 - Sydney, NSW, Australia
Duration: 2013 Dec 12013 Dec 8

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
ISSN (Print)1550-5499

Other

Other2013 14th IEEE International Conference on Computer Vision, ICCV 2013
CountryAustralia
CitySydney, NSW
Period13/12/113/12/8

Fingerprint

Markov processes
Spatial distribution
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Jiang, B., Zhang, L., Lu, H., Yang, C., & Yang, M. H. (2013). Saliency detection via absorbing Markov Chain. In Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013 (pp. 1665-1672). [6751317] (Proceedings of the IEEE International Conference on Computer Vision). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCV.2013.209
Jiang, Bowen ; Zhang, Lihe ; Lu, Huchuan ; Yang, Chuan ; Yang, Ming Hsuan. / Saliency detection via absorbing Markov Chain. Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013. Institute of Electrical and Electronics Engineers Inc., 2013. pp. 1665-1672 (Proceedings of the IEEE International Conference on Computer Vision).
@inproceedings{320896e7ce0a4155aaf4e37389d43f10,
title = "Saliency detection via absorbing Markov Chain",
abstract = "In this paper, we formulate saliency detection via absorbing Markov chain on an image graph model. We jointly consider the appearance divergence and spatial distribution of salient objects and the background. The virtual boundary nodes are chosen as the absorbing nodes in a Markov chain and the absorbed time from each transient node to boundary absorbing nodes is computed. The absorbed time of transient node measures its global similarity with all absorbing nodes, and thus salient objects can be consistently separated from the background when the absorbed time is used as a metric. Since the time from transient node to absorbing nodes relies on the weights on the path and their spatial distance, the background region on the center of image may be salient. We further exploit the equilibrium distribution in an ergodic Markov chain to reduce the absorbed time in the long-range smooth background regions. Extensive experiments on four benchmark datasets demonstrate robustness and efficiency of the proposed method against the state-of-the-art methods.",
author = "Bowen Jiang and Lihe Zhang and Huchuan Lu and Chuan Yang and Yang, {Ming Hsuan}",
year = "2013",
month = "1",
day = "1",
doi = "10.1109/ICCV.2013.209",
language = "English",
isbn = "9781479928392",
series = "Proceedings of the IEEE International Conference on Computer Vision",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1665--1672",
booktitle = "Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013",
address = "United States",

}

Jiang, B, Zhang, L, Lu, H, Yang, C & Yang, MH 2013, Saliency detection via absorbing Markov Chain. in Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013., 6751317, Proceedings of the IEEE International Conference on Computer Vision, Institute of Electrical and Electronics Engineers Inc., pp. 1665-1672, 2013 14th IEEE International Conference on Computer Vision, ICCV 2013, Sydney, NSW, Australia, 13/12/1. https://doi.org/10.1109/ICCV.2013.209

Saliency detection via absorbing Markov Chain. / Jiang, Bowen; Zhang, Lihe; Lu, Huchuan; Yang, Chuan; Yang, Ming Hsuan.

Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013. Institute of Electrical and Electronics Engineers Inc., 2013. p. 1665-1672 6751317 (Proceedings of the IEEE International Conference on Computer Vision).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Saliency detection via absorbing Markov Chain

AU - Jiang, Bowen

AU - Zhang, Lihe

AU - Lu, Huchuan

AU - Yang, Chuan

AU - Yang, Ming Hsuan

PY - 2013/1/1

Y1 - 2013/1/1

N2 - In this paper, we formulate saliency detection via absorbing Markov chain on an image graph model. We jointly consider the appearance divergence and spatial distribution of salient objects and the background. The virtual boundary nodes are chosen as the absorbing nodes in a Markov chain and the absorbed time from each transient node to boundary absorbing nodes is computed. The absorbed time of transient node measures its global similarity with all absorbing nodes, and thus salient objects can be consistently separated from the background when the absorbed time is used as a metric. Since the time from transient node to absorbing nodes relies on the weights on the path and their spatial distance, the background region on the center of image may be salient. We further exploit the equilibrium distribution in an ergodic Markov chain to reduce the absorbed time in the long-range smooth background regions. Extensive experiments on four benchmark datasets demonstrate robustness and efficiency of the proposed method against the state-of-the-art methods.

AB - In this paper, we formulate saliency detection via absorbing Markov chain on an image graph model. We jointly consider the appearance divergence and spatial distribution of salient objects and the background. The virtual boundary nodes are chosen as the absorbing nodes in a Markov chain and the absorbed time from each transient node to boundary absorbing nodes is computed. The absorbed time of transient node measures its global similarity with all absorbing nodes, and thus salient objects can be consistently separated from the background when the absorbed time is used as a metric. Since the time from transient node to absorbing nodes relies on the weights on the path and their spatial distance, the background region on the center of image may be salient. We further exploit the equilibrium distribution in an ergodic Markov chain to reduce the absorbed time in the long-range smooth background regions. Extensive experiments on four benchmark datasets demonstrate robustness and efficiency of the proposed method against the state-of-the-art methods.

UR - http://www.scopus.com/inward/record.url?scp=84898794697&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898794697&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2013.209

DO - 10.1109/ICCV.2013.209

M3 - Conference contribution

AN - SCOPUS:84898794697

SN - 9781479928392

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 1665

EP - 1672

BT - Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Jiang B, Zhang L, Lu H, Yang C, Yang MH. Saliency detection via absorbing Markov Chain. In Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013. Institute of Electrical and Electronics Engineers Inc. 2013. p. 1665-1672. 6751317. (Proceedings of the IEEE International Conference on Computer Vision). https://doi.org/10.1109/ICCV.2013.209