Presentation 2011-02-22
Evaluating Conventional Saliency Map Models for Estimating Human Egocentric Visual Attention
Kentaro YAMADA, Yusuke SUGANO, Takahiro OKABE, Yoichi SATO, Akihiro SUGIMOTO, Kazuo HIRAKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The validity of using conventional saliency map models to predict human attention was investigated for video captured with an egocentric camera. To evaluate the validity of using saliency map models for egocentric vision, an experiment was carried out to examine the correlation between saliency maps and measured gaze points for egocentric vision. The results show that conventional models can predict visually salient regions better than chance for egocentric vision and that the accuracy decreases significantly with an increase in visual motion induced by egomotion, which is presumably compensated for in the human visual system. This latter finding indicates that a visual saliency model is needed that can better predict human visual attention from egocentric videos.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Visual saliency / Visual attention / Gaze / First person vision
Paper # HIP2010-94
Date of Issue

Conference Information
Committee HIP
Conference Date 2011/2/14(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Human Information Processing (HIP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Evaluating Conventional Saliency Map Models for Estimating Human Egocentric Visual Attention
Sub Title (in English)
Keyword(1) Visual saliency
Keyword(2) Visual attention
Keyword(3) Gaze
Keyword(4) First person vision
1st Author's Name Kentaro YAMADA
1st Author's Affiliation Institute of Industrial Science, The University of Tokyo()
2nd Author's Name Yusuke SUGANO
2nd Author's Affiliation Institute of Industrial Science, The University of Tokyo
3rd Author's Name Takahiro OKABE
3rd Author's Affiliation Institute of Industrial Science, The University of Tokyo
4th Author's Name Yoichi SATO
4th Author's Affiliation Institute of Industrial Science, The University of Tokyo
5th Author's Name Akihiro SUGIMOTO
5th Author's Affiliation National Institute of Informatics
6th Author's Name Kazuo HIRAKI
6th Author's Affiliation Graduate School of Arts and Sciences, The University of Tokyo
Date 2011-02-22
Paper # HIP2010-94
Volume (vol) vol.110
Number (no) 422
Page pp.pp.-
#Pages 6
Date of Issue