Off-campus University of Richmond users: To download campus access theses, please use the following link to log in to our proxy server with your university username and password.
Date of Award
5-2025
Document Type
Restricted Thesis: Campus only access
Degree Name
Bachelor of Science
Department
Computer Science
First Advisor
Dr. Catherine Finegan-Dollak
Abstract
Gaze estimation is a well-explored task in computer vision and is useful for research in marketing and vision sciences. Previous appearance-based models rely on data collected in highly controlled conditions (stationary cameras or lab settings) which tends to generalize poorly to other real-world conditions. Webcams present a great opportunity for data collection but were underutilized in the existing datasets. This thesis introduces a new webcam gaze estimation dataset (WEyeDS) and a set of validation experiments aimed at addressing these shortcomings.
Recommended Citation
Evdokimov, Anatolii, "Webcam Gaze Estimation in Unconstrained Environments" (2025). Honors Theses. 1815.
https://scholarship.richmond.edu/honors-theses/1815
