PulseAugur
LIVE 12:24:43
research · [1 source] ·
0
research

New method improves real-time line assignment for reading gaze data

Researchers have developed a new method called CONF-LA to improve the accuracy of assigning eye-tracking fixations to specific lines of text during reading. This approach integrates knowledge of reading behavior with likelihoods of lines to assign fixations, deferring assignments when uncertainty is high. CONF-LA demonstrates stable performance in post hoc analysis and significantly reduces the gap between online and offline analysis, with a low per-fixation latency of 0.348 ms. It shows particular effectiveness with children's data, improving median accuracies on regressions. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Improves accuracy and reduces latency in real-time analysis of reading gaze data, potentially aiding educational and accessibility tools.

RANK_REASON Academic paper detailing a new method for analyzing reading gaze data.

Read on arXiv cs.LG →

COVERAGE [1]

  1. arXiv cs.LG TIER_1 · Franziska Kaltenberger, Wei-Ling Chen, Enkeleda Thaqi, Enkelejda Kasneci ·

    Sure About That Line? Approaching Confidence-Based, Real-Time Line Assignment in Reading Gaze Data

    arXiv:2605.00033v1 Announce Type: cross Abstract: Remote and webcam-based eye tracking in multi-line reading suffers from various noise factors and layout ambiguity, precisely where real-time reading support needs reliable, per-fixation line assignment. Prior work largely address…