Visual attention analysis by pseudo gravitational field

Yezhou Yang, Mingli Song, Na Li, Jiajun Bu, Chun Chen

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

6 Citations (Scopus)

Abstract

As a crucial step of the visual cognition and perception, visual attention analysis shows great importance in many research or application areas. In this paper, we treat this problem from a new angle, inspired by the classic gravitational field theory. By defining "mass" of each pixel, we compute "force" between them to obtain a so-called pseudo gravitational field over an image. Then, we propose an iteration algorithm to simulate the movement of the fixation points affected by this field. Finally, stable visual attention points or areas are obtained when those fixation points finally aggregate around some special pixels or areas. The main contributions are threefold: (1) by introducing classic gravitational field theory into visual attention analysis, a new point of view is proposed; (2) a competition scheme is constructed and the meaning of attraction can be applied into visual attention analysis intuitively; (3) by using pixels into computation through down sampling, a faster analysis method is achieved. The experimental result shows that our method is effective and consistent with the generally accepted definition of visual attention.

Original languageEnglish (US)
Title of host publicationMM'09 - Proceedings of the 2009 ACM Multimedia Conference, with Co-located Workshops and Symposiums
Pages553-556
Number of pages4
DOIs
StatePublished - 2009
Externally publishedYes
Event17th ACM International Conference on Multimedia, MM'09, with Co-located Workshops and Symposiums - Beijing, China
Duration: Oct 19 2009Oct 24 2009

Other

Other17th ACM International Conference on Multimedia, MM'09, with Co-located Workshops and Symposiums
CountryChina
CityBeijing
Period10/19/0910/24/09

Fingerprint

Pixels
Sampling

Keywords

  • Attention analysis
  • Gravitational field
  • Simulation algorithm

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Yang, Y., Song, M., Li, N., Bu, J., & Chen, C. (2009). Visual attention analysis by pseudo gravitational field. In MM'09 - Proceedings of the 2009 ACM Multimedia Conference, with Co-located Workshops and Symposiums (pp. 553-556) https://doi.org/10.1145/1631272.1631354

Visual attention analysis by pseudo gravitational field. / Yang, Yezhou; Song, Mingli; Li, Na; Bu, Jiajun; Chen, Chun.

MM'09 - Proceedings of the 2009 ACM Multimedia Conference, with Co-located Workshops and Symposiums. 2009. p. 553-556.

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

Yang, Y, Song, M, Li, N, Bu, J & Chen, C 2009, Visual attention analysis by pseudo gravitational field. in MM'09 - Proceedings of the 2009 ACM Multimedia Conference, with Co-located Workshops and Symposiums. pp. 553-556, 17th ACM International Conference on Multimedia, MM'09, with Co-located Workshops and Symposiums, Beijing, China, 10/19/09. https://doi.org/10.1145/1631272.1631354
Yang Y, Song M, Li N, Bu J, Chen C. Visual attention analysis by pseudo gravitational field. In MM'09 - Proceedings of the 2009 ACM Multimedia Conference, with Co-located Workshops and Symposiums. 2009. p. 553-556 https://doi.org/10.1145/1631272.1631354
Yang, Yezhou ; Song, Mingli ; Li, Na ; Bu, Jiajun ; Chen, Chun. / Visual attention analysis by pseudo gravitational field. MM'09 - Proceedings of the 2009 ACM Multimedia Conference, with Co-located Workshops and Symposiums. 2009. pp. 553-556
@inproceedings{a950224b373b47b7b7ef07094fc01805,
title = "Visual attention analysis by pseudo gravitational field",
abstract = "As a crucial step of the visual cognition and perception, visual attention analysis shows great importance in many research or application areas. In this paper, we treat this problem from a new angle, inspired by the classic gravitational field theory. By defining {"}mass{"} of each pixel, we compute {"}force{"} between them to obtain a so-called pseudo gravitational field over an image. Then, we propose an iteration algorithm to simulate the movement of the fixation points affected by this field. Finally, stable visual attention points or areas are obtained when those fixation points finally aggregate around some special pixels or areas. The main contributions are threefold: (1) by introducing classic gravitational field theory into visual attention analysis, a new point of view is proposed; (2) a competition scheme is constructed and the meaning of attraction can be applied into visual attention analysis intuitively; (3) by using pixels into computation through down sampling, a faster analysis method is achieved. The experimental result shows that our method is effective and consistent with the generally accepted definition of visual attention.",
keywords = "Attention analysis, Gravitational field, Simulation algorithm",
author = "Yezhou Yang and Mingli Song and Na Li and Jiajun Bu and Chun Chen",
year = "2009",
doi = "10.1145/1631272.1631354",
language = "English (US)",
isbn = "9781605586083",
pages = "553--556",
booktitle = "MM'09 - Proceedings of the 2009 ACM Multimedia Conference, with Co-located Workshops and Symposiums",

}

TY - GEN

T1 - Visual attention analysis by pseudo gravitational field

AU - Yang, Yezhou

AU - Song, Mingli

AU - Li, Na

AU - Bu, Jiajun

AU - Chen, Chun

PY - 2009

Y1 - 2009

N2 - As a crucial step of the visual cognition and perception, visual attention analysis shows great importance in many research or application areas. In this paper, we treat this problem from a new angle, inspired by the classic gravitational field theory. By defining "mass" of each pixel, we compute "force" between them to obtain a so-called pseudo gravitational field over an image. Then, we propose an iteration algorithm to simulate the movement of the fixation points affected by this field. Finally, stable visual attention points or areas are obtained when those fixation points finally aggregate around some special pixels or areas. The main contributions are threefold: (1) by introducing classic gravitational field theory into visual attention analysis, a new point of view is proposed; (2) a competition scheme is constructed and the meaning of attraction can be applied into visual attention analysis intuitively; (3) by using pixels into computation through down sampling, a faster analysis method is achieved. The experimental result shows that our method is effective and consistent with the generally accepted definition of visual attention.

AB - As a crucial step of the visual cognition and perception, visual attention analysis shows great importance in many research or application areas. In this paper, we treat this problem from a new angle, inspired by the classic gravitational field theory. By defining "mass" of each pixel, we compute "force" between them to obtain a so-called pseudo gravitational field over an image. Then, we propose an iteration algorithm to simulate the movement of the fixation points affected by this field. Finally, stable visual attention points or areas are obtained when those fixation points finally aggregate around some special pixels or areas. The main contributions are threefold: (1) by introducing classic gravitational field theory into visual attention analysis, a new point of view is proposed; (2) a competition scheme is constructed and the meaning of attraction can be applied into visual attention analysis intuitively; (3) by using pixels into computation through down sampling, a faster analysis method is achieved. The experimental result shows that our method is effective and consistent with the generally accepted definition of visual attention.

KW - Attention analysis

KW - Gravitational field

KW - Simulation algorithm

UR - http://www.scopus.com/inward/record.url?scp=72449139571&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=72449139571&partnerID=8YFLogxK

U2 - 10.1145/1631272.1631354

DO - 10.1145/1631272.1631354

M3 - Conference contribution

AN - SCOPUS:72449139571

SN - 9781605586083

SP - 553

EP - 556

BT - MM'09 - Proceedings of the 2009 ACM Multimedia Conference, with Co-located Workshops and Symposiums

ER -