Cognitive model of human visual search with saliency and scene context for real-world images

Yoonhyung Choi, Jinsung Han, Hyungseok Oh, Rohae Myung

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

Abstract

The previous Adaptive Control of Thought-Rational (ACT-R) cognitive architecture model has limitations in the sense that it cannot accurately predict human visual search for real-world images because scene context which could be as important as saliency is not included. Thus, this study proposed ACT-R cognitive modeling with saliency and scene context in parallel for human visual search. Then, the validation of the model was performed by comparing with eye-tracking experimental data. Results show that the model data was quite well fit with the eye-tracking data. In conclusion, the modeling method proposed in this study should be used, in order to predict actual human visual search using both strategies selectively for real-world image.

Original languageEnglish
Title of host publication2015 International Annual Meeting of the Human Factors and Ergonomics Society, HFES 2015
PublisherHuman Factors an Ergonomics Society Inc.
Pages706-710
Number of pages5
Volume2015-January
ISBN (Electronic)9780945289470
DOIs
Publication statusPublished - 2015
Event59th International Annual Meeting of the Human Factors and Ergonomics Society, HFES 2014 - Los Angeles, United States
Duration: 2015 Oct 262015 Oct 30

Other

Other59th International Annual Meeting of the Human Factors and Ergonomics Society, HFES 2014
CountryUnited States
CityLos Angeles
Period15/10/2615/10/30

ASJC Scopus subject areas

  • Human Factors and Ergonomics

Cite this

Choi, Y., Han, J., Oh, H., & Myung, R. (2015). Cognitive model of human visual search with saliency and scene context for real-world images. In 2015 International Annual Meeting of the Human Factors and Ergonomics Society, HFES 2015 (Vol. 2015-January, pp. 706-710). Human Factors an Ergonomics Society Inc.. https://doi.org/10.1177/1541931215591153

Cognitive model of human visual search with saliency and scene context for real-world images. / Choi, Yoonhyung; Han, Jinsung; Oh, Hyungseok; Myung, Rohae.

2015 International Annual Meeting of the Human Factors and Ergonomics Society, HFES 2015. Vol. 2015-January Human Factors an Ergonomics Society Inc., 2015. p. 706-710.

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

Choi, Y, Han, J, Oh, H & Myung, R 2015, Cognitive model of human visual search with saliency and scene context for real-world images. in 2015 International Annual Meeting of the Human Factors and Ergonomics Society, HFES 2015. vol. 2015-January, Human Factors an Ergonomics Society Inc., pp. 706-710, 59th International Annual Meeting of the Human Factors and Ergonomics Society, HFES 2014, Los Angeles, United States, 15/10/26. https://doi.org/10.1177/1541931215591153
Choi Y, Han J, Oh H, Myung R. Cognitive model of human visual search with saliency and scene context for real-world images. In 2015 International Annual Meeting of the Human Factors and Ergonomics Society, HFES 2015. Vol. 2015-January. Human Factors an Ergonomics Society Inc. 2015. p. 706-710 https://doi.org/10.1177/1541931215591153
Choi, Yoonhyung ; Han, Jinsung ; Oh, Hyungseok ; Myung, Rohae. / Cognitive model of human visual search with saliency and scene context for real-world images. 2015 International Annual Meeting of the Human Factors and Ergonomics Society, HFES 2015. Vol. 2015-January Human Factors an Ergonomics Society Inc., 2015. pp. 706-710
@inproceedings{a16e03d70bd443b19cb7b2318c7535db,
title = "Cognitive model of human visual search with saliency and scene context for real-world images",
abstract = "The previous Adaptive Control of Thought-Rational (ACT-R) cognitive architecture model has limitations in the sense that it cannot accurately predict human visual search for real-world images because scene context which could be as important as saliency is not included. Thus, this study proposed ACT-R cognitive modeling with saliency and scene context in parallel for human visual search. Then, the validation of the model was performed by comparing with eye-tracking experimental data. Results show that the model data was quite well fit with the eye-tracking data. In conclusion, the modeling method proposed in this study should be used, in order to predict actual human visual search using both strategies selectively for real-world image.",
author = "Yoonhyung Choi and Jinsung Han and Hyungseok Oh and Rohae Myung",
year = "2015",
doi = "10.1177/1541931215591153",
language = "English",
volume = "2015-January",
pages = "706--710",
booktitle = "2015 International Annual Meeting of the Human Factors and Ergonomics Society, HFES 2015",
publisher = "Human Factors an Ergonomics Society Inc.",

}

TY - GEN

T1 - Cognitive model of human visual search with saliency and scene context for real-world images

AU - Choi, Yoonhyung

AU - Han, Jinsung

AU - Oh, Hyungseok

AU - Myung, Rohae

PY - 2015

Y1 - 2015

N2 - The previous Adaptive Control of Thought-Rational (ACT-R) cognitive architecture model has limitations in the sense that it cannot accurately predict human visual search for real-world images because scene context which could be as important as saliency is not included. Thus, this study proposed ACT-R cognitive modeling with saliency and scene context in parallel for human visual search. Then, the validation of the model was performed by comparing with eye-tracking experimental data. Results show that the model data was quite well fit with the eye-tracking data. In conclusion, the modeling method proposed in this study should be used, in order to predict actual human visual search using both strategies selectively for real-world image.

AB - The previous Adaptive Control of Thought-Rational (ACT-R) cognitive architecture model has limitations in the sense that it cannot accurately predict human visual search for real-world images because scene context which could be as important as saliency is not included. Thus, this study proposed ACT-R cognitive modeling with saliency and scene context in parallel for human visual search. Then, the validation of the model was performed by comparing with eye-tracking experimental data. Results show that the model data was quite well fit with the eye-tracking data. In conclusion, the modeling method proposed in this study should be used, in order to predict actual human visual search using both strategies selectively for real-world image.

UR - http://www.scopus.com/inward/record.url?scp=84981747375&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84981747375&partnerID=8YFLogxK

U2 - 10.1177/1541931215591153

DO - 10.1177/1541931215591153

M3 - Conference contribution

AN - SCOPUS:84981747375

VL - 2015-January

SP - 706

EP - 710

BT - 2015 International Annual Meeting of the Human Factors and Ergonomics Society, HFES 2015

PB - Human Factors an Ergonomics Society Inc.

ER -