analiza aiqbench
GazeFS represents a significant advancement in human-computer interaction by leveraging historical gaze-head dynamics to forecast and stabilize target acquisition without requiring explicit target information at inference. The research demonstrates that incorporating variable-length history windows effectively reduces target error and dispersion, offering a robust framework for improving eye-tracking performance in real-time applications. This work bridges the gap between raw signal processing and task-aligned interaction, providing measurable improvements over baseline methods across diverse participant groups.
GazeFS: Target-Centered Gaze-Trajectory Forecasting and Stabilization from Gaze-Head History
arXiv:2609.03868v1 Announce Type: cross Abstract: Target-centered gaze interaction requires more than suppressing frame-to-frame fluctuations: target acquisition produces task-aligned changes in gaze-head dynamics, while a gaze trace may retain a persistent target-relative residual direction. We formulate gaze correction as online target-centered gaze-trajectory forecasting and stabilization and introduce GazeFS, which maps a variable-length gaze-head history to the next target-center direction and a short-horizon Search/Focus estimate without target information at inference. Across 7,960 acquisition episodes from 30 participants, Search-Focus differences remain stable under quality control, onset exclusion, and duration matching. History windows improve phase decoding over the current endpoint, but explicit task progress remains a strong control. Under the 30-participant, five-fold grouped out-of-fold protocol across three seeds, the reductions relative to raw hold in Focus episode bias, within-episode dispersion, and P90 target error are 0.182 degrees, 0.257 degrees, and 0.400 degrees, with participant-bootstrap 95% confidence intervals excluding zero. Endpoint-free replay from empty history preserves the Focus advantage and yields raw-network phase balanced accuracy/AUPRC of 0.925/0.993; coordinate controls further show that recent history contributes beyond explicit progress metadata. GazeFS therefore improves Focus target centering and empirical residual contraction while leaving temporal smoothness as a separate objective.
Abstract:Target-centered gaze interaction requires more than suppressing frame-to-frame fluctuations: target acquisition produces task-aligned changes in gaze-head dynamics, while a gaze trace may retain a persistent target-relative residual direction. We formulate gaze correction as online target-centered gaze-trajectory forecasting and stabilization and introduce GazeFS, which maps a variable-length gaze-head history to the next target-center direction and a short-horizon Search/Focus estimate without target information at inference. Across 7,960 acquisition episodes from 30 participants, Search-Focus differences remain stable under quality control, onset exclusion, and duration matching. History windows improve phase decoding over the current endpoint, but explicit task progress remains a strong control. Under the 30-participant, five-fold grouped out-of-fold protocol across three seeds, the reductions relative to raw hold in Focus episode bias, within-episode dispersion, and P90 target error are 0.182 degrees, 0.257 degrees, and 0.400 degrees, with participant-bootstrap 95% confidence intervals excluding zero. Endpoint-free replay from empty history preserves the Focus advantage and yields raw-network phase balanced accuracy/AUPRC of 0.925/0.993; coordinate controls further show that recent history contributes beyond explicit progress metadata. GazeFS therefore improves Focus target centering and empirical residual contraction while leaving temporal smoothness as a separate objective.
Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
arXiv:2609.03868 [cs.HC]
(or arXiv:2609.03868v1 [cs.HC] for this version)
https://doi.org/10.48550/arXiv.2609.03868 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 284 cuvinte
Subiecte conexe
From Rainfall to Road-Network Functionality: Transferable Graph Forecasting for Flood-Disrupted Transportation Networks
arXiv · 14 oct. 2026
News
Quantum Computing Report · 25 iul. 2026
Microsoft’s AI chief says superintelligence is near, but won’t take your job
The Verge · 8 iun. 2026
D . A . T . E ., A LEADER IN THERMAL INNOVATION FOR CRITICAL TECHNOLOGIES , ANNOUNCES ITS PROPOSED INITIAL PUBLIC OFFERING ON EURONEXT GROWTH IN PARIS
finanznachrichten.de · 30 iul. 2026