TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Exploiting inter-image similarity and ensemble of extreme learners for fixation prediction using deep features

Tutkimustuotosvertaisarvioitu

Standard

Exploiting inter-image similarity and ensemble of extreme learners for fixation prediction using deep features. / Tavakoli, Hamed R.; Borji, Ali; Laaksonen, Jorma; Rahtu, Esa.

julkaisussa: Neurocomputing, Vuosikerta 244, 28.06.2017, s. 10-18.

Tutkimustuotosvertaisarvioitu

Harvard

Tavakoli, HR, Borji, A, Laaksonen, J & Rahtu, E 2017, 'Exploiting inter-image similarity and ensemble of extreme learners for fixation prediction using deep features', Neurocomputing, Vuosikerta. 244, Sivut 10-18. https://doi.org/10.1016/j.neucom.2017.03.018

APA

Vancouver

Author

Tavakoli, Hamed R. ; Borji, Ali ; Laaksonen, Jorma ; Rahtu, Esa. / Exploiting inter-image similarity and ensemble of extreme learners for fixation prediction using deep features. Julkaisussa: Neurocomputing. 2017 ; Vuosikerta 244. Sivut 10-18.

Bibtex - Lataa

@article{5633eaff4eba42fcb0bc3117048174da,
title = "Exploiting inter-image similarity and ensemble of extreme learners for fixation prediction using deep features",
abstract = "This paper presents a novel fixation prediction and saliency modeling framework based on inter-image similarities and ensemble of Extreme Learning Machines (ELM). The proposed framework is inspired by two observations, (1) the contextual information of a scene along with low-level visual cues modulates attention, (2) the influence of scene memorability on eye movement patterns caused by the resemblance of a scene to a former visual experience. Motivated by such observations, we develop a framework that estimates the saliency of a given image using an ensemble of extreme learners, each trained on an image similar to the input image. That is, after retrieving a set of similar images for a given image, a saliency predictor is learnt from each of the images in the retrieved image set using an ELM, resulting in an ensemble. The saliency of the given image is then measured in terms of the mean of predicted saliency value by the ensemble's members. (C) 2017 Elsevier B.V. All rights reserved.",
keywords = "Visual attention, Saliency prediction, Fixation prediction, Inter-image similarity, Extreme learning machines, VISUAL-ATTENTION, OBJECT DETECTION, SALIENCY DETECTION, EYE GUIDANCE, MODEL, SCENE, SEARCH, RECOGNITION, SYSTEM",
author = "Tavakoli, {Hamed R.} and Ali Borji and Jorma Laaksonen and Esa Rahtu",
note = "INT=sgn,{"}Rahtu, Esa{"}",
year = "2017",
month = "6",
day = "28",
doi = "10.1016/j.neucom.2017.03.018",
language = "English",
volume = "244",
pages = "10--18",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier Science B.V.",

}

RIS (suitable for import to EndNote) - Lataa

TY - JOUR

T1 - Exploiting inter-image similarity and ensemble of extreme learners for fixation prediction using deep features

AU - Tavakoli, Hamed R.

AU - Borji, Ali

AU - Laaksonen, Jorma

AU - Rahtu, Esa

N1 - INT=sgn,"Rahtu, Esa"

PY - 2017/6/28

Y1 - 2017/6/28

N2 - This paper presents a novel fixation prediction and saliency modeling framework based on inter-image similarities and ensemble of Extreme Learning Machines (ELM). The proposed framework is inspired by two observations, (1) the contextual information of a scene along with low-level visual cues modulates attention, (2) the influence of scene memorability on eye movement patterns caused by the resemblance of a scene to a former visual experience. Motivated by such observations, we develop a framework that estimates the saliency of a given image using an ensemble of extreme learners, each trained on an image similar to the input image. That is, after retrieving a set of similar images for a given image, a saliency predictor is learnt from each of the images in the retrieved image set using an ELM, resulting in an ensemble. The saliency of the given image is then measured in terms of the mean of predicted saliency value by the ensemble's members. (C) 2017 Elsevier B.V. All rights reserved.

AB - This paper presents a novel fixation prediction and saliency modeling framework based on inter-image similarities and ensemble of Extreme Learning Machines (ELM). The proposed framework is inspired by two observations, (1) the contextual information of a scene along with low-level visual cues modulates attention, (2) the influence of scene memorability on eye movement patterns caused by the resemblance of a scene to a former visual experience. Motivated by such observations, we develop a framework that estimates the saliency of a given image using an ensemble of extreme learners, each trained on an image similar to the input image. That is, after retrieving a set of similar images for a given image, a saliency predictor is learnt from each of the images in the retrieved image set using an ELM, resulting in an ensemble. The saliency of the given image is then measured in terms of the mean of predicted saliency value by the ensemble's members. (C) 2017 Elsevier B.V. All rights reserved.

KW - Visual attention

KW - Saliency prediction

KW - Fixation prediction

KW - Inter-image similarity

KW - Extreme learning machines

KW - VISUAL-ATTENTION

KW - OBJECT DETECTION

KW - SALIENCY DETECTION

KW - EYE GUIDANCE

KW - MODEL

KW - SCENE

KW - SEARCH

KW - RECOGNITION

KW - SYSTEM

U2 - 10.1016/j.neucom.2017.03.018

DO - 10.1016/j.neucom.2017.03.018

M3 - Article

VL - 244

SP - 10

EP - 18

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

ER -