TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Probabilistic saliency estimation

Tutkimustuotosvertaisarvioitu

Standard

Probabilistic saliency estimation. / Aytekin, Caglar; Iosifidis, Alexandros; Gabbouj, Moncef.

julkaisussa: Pattern Recognition, Vuosikerta 74, 2018, s. 359-372.

Tutkimustuotosvertaisarvioitu

Harvard

Aytekin, C, Iosifidis, A & Gabbouj, M 2018, 'Probabilistic saliency estimation', Pattern Recognition, Vuosikerta. 74, Sivut 359-372. https://doi.org/10.1016/j.patcog.2017.09.023

APA

Aytekin, C., Iosifidis, A., & Gabbouj, M. (2018). Probabilistic saliency estimation. Pattern Recognition, 74, 359-372. https://doi.org/10.1016/j.patcog.2017.09.023

Vancouver

Aytekin C, Iosifidis A, Gabbouj M. Probabilistic saliency estimation. Pattern Recognition. 2018;74:359-372. https://doi.org/10.1016/j.patcog.2017.09.023

Author

Aytekin, Caglar ; Iosifidis, Alexandros ; Gabbouj, Moncef. / Probabilistic saliency estimation. Julkaisussa: Pattern Recognition. 2018 ; Vuosikerta 74. Sivut 359-372.

Bibtex - Lataa

@article{10b34fd0bec74f7186966b7c67965027,
title = "Probabilistic saliency estimation",
abstract = "In this paper, we model the salient object detection problem under a probabilistic framework encoding the boundary connectivity saliency cue and smoothness constraints into an optimization problem. We show that this problem has a closed form global optimum solution, which estimates the salient object. We further show that along with the probabilistic framework, the proposed method also enjoys a wide range of interpretations, i.e. graph cut, diffusion maps and one-class classification. With an analysis according to these interpretations, we also find that our proposed method provides approximations to the global optimum to another criterion that integrates local/global contrast and large area saliency cues. The proposed unsupervised approach achieves mostly leading performance compared to the state-of-the-art unsupervised algorithms over a large set of salient object detection datasets including around 17k images for several evaluation metrics. Furthermore, the computational complexity of the proposed method is favorable/comparable to many state-of-the-art unsupervised techniques.",
keywords = "Diffusion maps, One-class classification, Probabilistic model, Saliency, Salient object detection, Spectral graph cut",
author = "Caglar Aytekin and Alexandros Iosifidis and Moncef Gabbouj",
year = "2018",
doi = "10.1016/j.patcog.2017.09.023",
language = "English",
volume = "74",
pages = "359--372",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "ELSEVIER SCI LTD",

}

RIS (suitable for import to EndNote) - Lataa

TY - JOUR

T1 - Probabilistic saliency estimation

AU - Aytekin, Caglar

AU - Iosifidis, Alexandros

AU - Gabbouj, Moncef

PY - 2018

Y1 - 2018

N2 - In this paper, we model the salient object detection problem under a probabilistic framework encoding the boundary connectivity saliency cue and smoothness constraints into an optimization problem. We show that this problem has a closed form global optimum solution, which estimates the salient object. We further show that along with the probabilistic framework, the proposed method also enjoys a wide range of interpretations, i.e. graph cut, diffusion maps and one-class classification. With an analysis according to these interpretations, we also find that our proposed method provides approximations to the global optimum to another criterion that integrates local/global contrast and large area saliency cues. The proposed unsupervised approach achieves mostly leading performance compared to the state-of-the-art unsupervised algorithms over a large set of salient object detection datasets including around 17k images for several evaluation metrics. Furthermore, the computational complexity of the proposed method is favorable/comparable to many state-of-the-art unsupervised techniques.

AB - In this paper, we model the salient object detection problem under a probabilistic framework encoding the boundary connectivity saliency cue and smoothness constraints into an optimization problem. We show that this problem has a closed form global optimum solution, which estimates the salient object. We further show that along with the probabilistic framework, the proposed method also enjoys a wide range of interpretations, i.e. graph cut, diffusion maps and one-class classification. With an analysis according to these interpretations, we also find that our proposed method provides approximations to the global optimum to another criterion that integrates local/global contrast and large area saliency cues. The proposed unsupervised approach achieves mostly leading performance compared to the state-of-the-art unsupervised algorithms over a large set of salient object detection datasets including around 17k images for several evaluation metrics. Furthermore, the computational complexity of the proposed method is favorable/comparable to many state-of-the-art unsupervised techniques.

KW - Diffusion maps

KW - One-class classification

KW - Probabilistic model

KW - Saliency

KW - Salient object detection

KW - Spectral graph cut

U2 - 10.1016/j.patcog.2017.09.023

DO - 10.1016/j.patcog.2017.09.023

M3 - Article

VL - 74

SP - 359

EP - 372

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

ER -