Skip to main content

Dual input stream transformer for eye-tracking line assignment.

Mercier, T. M, Budka, M., Vasilev, M. R., Kirkby, J. A, Angele, B. and Slattery, T. J., 2023. Dual input stream transformer for eye-tracking line assignment. Transactions on pattern analysis and machine intelligence. (In Press)

Full text available as:

[img] PDF
paper_post_accept_for_final_sub_with_editor_changes_and_ackn.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial.

1MB
[img] PDF
paper_suppl_post_2nd_review.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial.

1MB

Abstract

We introduce a novel Dual Input Stream Transformer (DIST) for the challenging problem of assigning fixation points from eye-tracking data collected during passage reading to the line of text that the reader was actually focused on. This post-processing step is crucial for analysis of the reading data due to the presence of noise in the form of vertical drift. We evaluate DIST against eleven classical approaches on a comprehensive suite of nine diverse datasets. We demonstrate that combining multiple instances of the DIST model in an ensemble achieves high accuracy across all datasets. Further combining the DIST ensemble with the best classical approach yields an average accuracy of 98.17 %. Our approach presents a significant step towards addressing the bottleneck of manual line assignment in reading research. Through extensive analysis and ablation studies, we identify key factors that contribute to DIST’s success, including the incorporation of line overlap features and the use of a second input stream. Via rigorous evaluation, we demonstrate that DIST is robust to various experimental setups, making it a safe first choice for practitioners in the field.

Item Type:Article
ISSN:1939-3539
Uncontrolled Keywords:Machine Learning; Psychology; Pattern Recognition; Artificial Intelligence; Computer vision
Group:Faculty of Science & Technology
ID Code:39913
Deposited By: Symplectic RT2
Deposited On:07 Jun 2024 16:06
Last Modified:07 Jun 2024 16:06

Downloads

Downloads per month over past year

More statistics for this item...
Repository Staff Only -