USGaze: Temporal Gaze Estimation via a Unified State-Space Modeling Framework
Electronics · 2026-03-30 · 15 (7) · 1430
DOI: 10.3390/electronics15071430 ↗At a glance
Journal article in Electronics, published online on 2026-03-30. Written by Gefan Sun and 2 co-authors. 28 references. The full text is freely available (open access, CC BY 4.0). Funded by: Key Research and Development Program of Ningbo, Key Research and Development Program of Zhejiang.
Abstract (original language)
Existing appearance-based and video-based gaze estimation methods mainly rely on frame-wise prediction or local-window temporal fusion, which limits their ability to model long-range dependencies and to explicitly suppress output-level jitter. This leaves a gap in unified temporal gaze estimation frameworks that jointly address contextual feature aggregation and prediction-level stabilization. To address this limitation, we propose a unified state-space temporal gaze estimation framework to improve both angular accuracy and temporal consistency. Specifically, consecutive eye image sequences are mapped into a shared latent state space, where spatial appearance cues and inter-frame dynamics are jointly modeled. A feature-level temporal aggregation module is further designed to adaptively reweight historical observations for the current estimate, and a prediction-level temporal correction module is introduced to suppress short-term fluctuations while preserving rapid gaze shifts. On the TEyeD dataset after quality screening, the proposed method achieves a 3D gaze MAE of 0.533°, compared with 0.96° for Model-aware and 3.18°–3.47° for the ResNet baselines reported in the original TEyeD paper, while maintaining manageable deployment overhead. These results indicate that the proposed framework provides a favorable balance between estimation accuracy, temporal stability, and practical efficiency.
Funding
- Key Research and Development Program of Ningbo
- Key Research and Development Program of Zhejiang
Cite
APA
Sun, G., Wang, Z., & Xia, Q. (2026). USGaze: Temporal Gaze Estimation via a Unified State-Space Modeling Framework. Electronics, 15(7), 1430. https://doi.org/10.3390/electronics15071430
Vancouver
Sun G, Wang Z, Xia Q. USGaze: Temporal Gaze Estimation via a Unified State-Space Modeling Framework. Electronics. 2026;15(7):1430. doi:10.3390/electronics15071430
BibTeX
@article{Sun2026,
author = {Sun, Gefan and Wang, Zhao and Xia, Qinghua},
title = {USGaze: Temporal Gaze Estimation via a Unified State-Space Modeling Framework},
journal = {Electronics},
year = {2026},
volume = {15},
number = {7},
pages = {1430},
doi = {10.3390/electronics15071430}
}
EUVIMED