Home > Research > Publications & Outputs > Deep salience

Links

View graph of relations

Deep salience: Visual salience modeling via deep belief propagation

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Deep salience: Visual salience modeling via deep belief propagation. / Jiang, Richard; Crookes, Danny.
Proceedings of the National Conference on Artificial Intelligence. AI Access Foundation, 2014. p. 2773-2779 (Proceedings of the National Conference on Artificial Intelligence; Vol. 4).

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Jiang, R & Crookes, D 2014, Deep salience: Visual salience modeling via deep belief propagation. in Proceedings of the National Conference on Artificial Intelligence. Proceedings of the National Conference on Artificial Intelligence, vol. 4, AI Access Foundation, pp. 2773-2779, 28th AAAI Conference on Artificial Intelligence, AAAI 2014, 26th Innovative Applications of Artificial Intelligence Conference, IAAI 2014 and the 5th Symposium on Educational Advances in Artificial Intelligence, EAAI 2014, Quebec City, Canada, 27/07/14. <https://dl.acm.org/citation.cfm?id=2892936>

APA

Jiang, R., & Crookes, D. (2014). Deep salience: Visual salience modeling via deep belief propagation. In Proceedings of the National Conference on Artificial Intelligence (pp. 2773-2779). (Proceedings of the National Conference on Artificial Intelligence; Vol. 4). AI Access Foundation. https://dl.acm.org/citation.cfm?id=2892936

Vancouver

Jiang R, Crookes D. Deep salience: Visual salience modeling via deep belief propagation. In Proceedings of the National Conference on Artificial Intelligence. AI Access Foundation. 2014. p. 2773-2779. (Proceedings of the National Conference on Artificial Intelligence).

Author

Jiang, Richard ; Crookes, Danny. / Deep salience : Visual salience modeling via deep belief propagation. Proceedings of the National Conference on Artificial Intelligence. AI Access Foundation, 2014. pp. 2773-2779 (Proceedings of the National Conference on Artificial Intelligence).

Bibtex

@inproceedings{3608729d2f8f42bd956ca97b712b59c4,
title = "Deep salience: Visual salience modeling via deep belief propagation",
abstract = "Visual salience is an intriguing phenomenon observed in biological neural systems. Numerous attempts have been made to model visual salience mathematically using various feature contrasts, either locally or globally. However, these algorithmic models tend to ignore the problem's biological solutions, in which visual salience appears to arise during the propagation of visual stimuli along the visual cortex. In this paper, inspired by the conjecture that salience arises from deep propagation along the visual cortex, we present a Deep Salience model where a multi-layer model based on successive Markov random fields (sMRF) is proposed to analyze the input image successively through its deep belief propagation. As a result, the foreground object can be automatically separated from the background in a fully unsupervised way. Experimental evaluation on the benchmark dataset validated that our Deep Salience model can consistently outperform eleven state-of-the-art salience models, yielding the higher rates in the precision-recall tests and attaining the best F-measure and mean-square error in the experiments.",
author = "Richard Jiang and Danny Crookes",
year = "2014",
month = jan,
day = "1",
language = "English",
series = "Proceedings of the National Conference on Artificial Intelligence",
publisher = "AI Access Foundation",
pages = "2773--2779",
booktitle = "Proceedings of the National Conference on Artificial Intelligence",
address = "United States",
note = "28th AAAI Conference on Artificial Intelligence, AAAI 2014, 26th Innovative Applications of Artificial Intelligence Conference, IAAI 2014 and the 5th Symposium on Educational Advances in Artificial Intelligence, EAAI 2014 ; Conference date: 27-07-2014 Through 31-07-2014",

}

RIS

TY - GEN

T1 - Deep salience

T2 - 28th AAAI Conference on Artificial Intelligence, AAAI 2014, 26th Innovative Applications of Artificial Intelligence Conference, IAAI 2014 and the 5th Symposium on Educational Advances in Artificial Intelligence, EAAI 2014

AU - Jiang, Richard

AU - Crookes, Danny

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Visual salience is an intriguing phenomenon observed in biological neural systems. Numerous attempts have been made to model visual salience mathematically using various feature contrasts, either locally or globally. However, these algorithmic models tend to ignore the problem's biological solutions, in which visual salience appears to arise during the propagation of visual stimuli along the visual cortex. In this paper, inspired by the conjecture that salience arises from deep propagation along the visual cortex, we present a Deep Salience model where a multi-layer model based on successive Markov random fields (sMRF) is proposed to analyze the input image successively through its deep belief propagation. As a result, the foreground object can be automatically separated from the background in a fully unsupervised way. Experimental evaluation on the benchmark dataset validated that our Deep Salience model can consistently outperform eleven state-of-the-art salience models, yielding the higher rates in the precision-recall tests and attaining the best F-measure and mean-square error in the experiments.

AB - Visual salience is an intriguing phenomenon observed in biological neural systems. Numerous attempts have been made to model visual salience mathematically using various feature contrasts, either locally or globally. However, these algorithmic models tend to ignore the problem's biological solutions, in which visual salience appears to arise during the propagation of visual stimuli along the visual cortex. In this paper, inspired by the conjecture that salience arises from deep propagation along the visual cortex, we present a Deep Salience model where a multi-layer model based on successive Markov random fields (sMRF) is proposed to analyze the input image successively through its deep belief propagation. As a result, the foreground object can be automatically separated from the background in a fully unsupervised way. Experimental evaluation on the benchmark dataset validated that our Deep Salience model can consistently outperform eleven state-of-the-art salience models, yielding the higher rates in the precision-recall tests and attaining the best F-measure and mean-square error in the experiments.

M3 - Conference contribution/Paper

AN - SCOPUS:84908180978

T3 - Proceedings of the National Conference on Artificial Intelligence

SP - 2773

EP - 2779

BT - Proceedings of the National Conference on Artificial Intelligence

PB - AI Access Foundation

Y2 - 27 July 2014 through 31 July 2014

ER -