Video
BibTex
@inproceedings{Li:2021:10.20380/GI2021.35,
author = {Li, Zhi and Zhao, Maozheng and Wang, Yifan and Rashidian, Sina and Baig, Furqan and Liu, Rui and Liu, Wanyu and Beaudouin-Lafon, Michel and Ellison, Brooke and Wang, Fusheng and Ramakrishnan, IV and Bi, Xiaojun},
title = {BayesGaze: A Bayesian Approach to Eye-Gaze Based Target Selection},
booktitle = {Proceedings of Graphics Interface 2021},
series = {GI 2021},
year = {2021},
issn = {0713-5424},
isbn = {978-0-9947868-6-9},
location = {Virtual Event},
pages = {231 -- 240},
numpages = {10},
doi = {10.20380/GI2021.35},
publisher = {Canadian Information Processing Society},
}
Abstract
Selecting targets accurately and quickly with eye-gaze input remains an open research question. In this paper, we introduce BayesGaze, a Bayesian approach of determining the selected target given an eye-gaze trajectory. This approach views each sampling point in an eye-gaze trajectory as a signal for selecting a target. It then uses the Bayes' theorem to calculate the posterior probability of selecting a target given a sampling point, and accumulates the posterior probabilities weighted by sampling interval to determine the selected target. The selection results are fed back to update the prior distribution of targets, which is modeled by a categorical distribution. Our investigation shows that BayesGaze improves target selection accuracy and speed over a dwell-based selection method, and the Center of Gravity Mapping (CM) method. Our research shows that both accumulating posterior and incorporating the prior are effective in improving the performance of eye-gaze based target selection.