EyeO: Autocalibrating Gaze Output with Gaze Input for Gaze Typing

VIEW PUBLICATION

Akanksha Saran

Jacob Alber

Cyril Zhang

Ann Paradiso

Danielle Bragg

John Langford*

* External authors

CHI 2025

2025

Abstract

Gaze tracking devices have the potential to expand interactivity greatly, yet miscalibration remains a significant barrier to use. As devices miscalibrate, people tend to compensate by intentionally offsetting their gaze, which makes detecting miscalibration from eye signals difficult. To help address this problem, we propose a novel approach to seamless calibration based on the insight that the system's model of eye gaze can be updated during reading (user does not compensate) to improve calibration for typing (user might compensate). To explore this approach, we built an auto-calibrating gaze typing prototype called EyeO and ran a user study with 20 participants. Our user study results suggest that seamless autocalibration can significantly improve typing efficiency and user experience.

Related Publications

Human-Interactive Robot Learning: Definition, Challenges, and Recommendations

THRI, 2025
Kim Baraka, Ifrah Idrees, Taylor Kessler Faulkner, Erdem Biyik, Serena Booth*, Mohamed Chetouani, Daniel Grollman, Akanksha Saran, Emmanuel Senft, Silvia Tulli, Anna-Lisa Vollmer, Antonio Andriella, Helen Beierling, Tiffany Horter, Jens Kober, Isaac Sheidlower, Matthew Taylor, Sanne van Waveren, Xuesu Xiao*

Robot learning from humans has been proposed and researched for several decades as a means to enable robots to learn new skills or adapt existing ones to new situations. Recent advances in artificial intelligence, including learning approaches like reinforcement learning and…

Prosody as an Informative Teaching Signal for Agent Learning: Exploratory Studies and Algorithmic Implications

, 2024
Akanksha Saran, Matilda Knierim, Sahil Jain, Murat Han Aydoğan, Kenneth Mitra, Kush Desai, Kim Baraka

Agent learning from human interaction often relies on explicit signals, but implicit social cues, such as prosody in speech, could provide valuable information for more effective learning. This paperadvocates for the integration of prosody as a teaching signal to enhance age…

Towards Principled Representation Learning from Videos for Reinforcement Learning

ICLR, 2024
Dipendra Misra*, Akanksha Saran, Tengyang Xie*, Alex Lamb*, John Langford*

We study pre-training representations for decision-making using video data, which is abundantly available for tasks such as game agents and software testing. Even though significant empirical advances have been made on this problem, a theoretical understanding remains absent…

SEE ALL

HOME
Publications
EyeO: Autocalibrating Gaze Output with Gaze Input for Gaze Typing

JOIN US

Shape the Future of AI with Sony AI

We want to hear from those of you who have a strong desire
to shape the future of AI.

LEARN MORE