Inferring human gaze from appearance via adaptive linear regression

Authors:
Feng Lu;Yusuke Sugano;Takahiro Okabe;Yoichi Sato
Affiliations:
Institute of Industrial Science, the University of Tokyo, Japan;Institute of Industrial Science, the University of Tokyo, Japan;Institute of Industrial Science, the University of Tokyo, Japan;Institute of Industrial Science, the University of Tokyo, Japan
Venue:
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
Year:
2011

Citing 0
Cited 3

Appearance-based gaze tracking with spectral clustering and semi-supervised Gaussian process regression

Proceedings of the 2013 Conference on Eye Tracking South Africa
A semi-automated system for accurate gaze coding in natural dyadic interactions

Proceedings of the 15th ACM on International conference on multimodal interaction
3D head pose and gaze tracking and their application to diverse multimodal tasks

Proceedings of the 15th ACM on International conference on multimodal interaction

Quantified Score

Hi-index	0.00

Visualization

Abstract

The problem of estimating human gaze from eye appearance is regarded as mapping high-dimensional features to low-dimensional target space. Conventional methods require densely obtained training samples on the eye appearance manifold, which results in a tedious calibration stage. In this paper, we introduce an adaptive linear regression (ALR) method for accurate mapping via sparsely collected training samples. The key idea is to adaptively find the subset of training samples where the test sample is most linearly representable. We solve the problem via l