Uncertainty-Aware General Gaze Following via Circular Direction Distribution Learning and Probabilistic Gaze Geometry Modeling
Journal of Eye Movement Research · 13.08.2026 · 19 (4) · 88
DOI: 10.3390/jemr19040088 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Eye Movement Research, online erschienen am 13.08.2026. Verfasst von Yanzhao Li und 3 weiteren Autor:innen. Beteiligte Einrichtung: College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin 150001, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
General gaze following aims to infer the region attended to by a person within a natural scene and offers a computational perspective on visual attention and social scene understanding. Existing direction-guided methods usually reduce gaze direction to a single vector or spatial mask. This deterministic treatment can obscure directional ambiguity, discard coexisting candidate directions, and propagate early estimation errors to gaze target localization when head cues are weak or multiple targets are plausible. To address these limitations, we propose an uncertainty-aware framework based on Circular Direction Distribution Learning (CDDL) and Probabilistic Gaze Geometry Modeling (PGGM). CDDL represents gaze direction as a 72-bin circular probability distribution under von Mises soft supervision, thereby preserving neighboring directional hypotheses before target localization. Rather than predicting a target space distribution directly, PGGM aggregates the direction distribution into 18 groups and projects the retained hypotheses into cone-like spatial probability fields, allowing spatial tolerance to expand with distance while preserving a channel-wise direction-to-region representation. The full probability volume is fused with the RGB scene image at the input level and processed by a ResNet-50-FPN network for gaze heatmap prediction. Controlled experiments on GazeFollow demonstrate competitive localization and support the contribution of direction-distribution learning and channel-wise geometric projection. Zero-shot transfer, dataset-level uncertainty and failure analyses, efficiency measurements, and qualitative results further indicate interpretable behavior together with domain-dependent and computational trade-offs.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin 150001, China.
- School of Economics and Management, Harbin Engineering University, Harbin 150001, China.
Zitieren
APA
Li, Y., Li, J., Zhang, X., & Liang, H. (2026). Uncertainty-Aware General Gaze Following via Circular Direction Distribution Learning and Probabilistic Gaze Geometry Modeling. Journal of Eye Movement Research, 19(4), 88. https://doi.org/10.3390/jemr19040088
Vancouver
Li Y, Li J, Zhang X, Liang H. Uncertainty-Aware General Gaze Following via Circular Direction Distribution Learning and Probabilistic Gaze Geometry Modeling. Journal of Eye Movement Research. 2026;19(4):88. doi:10.3390/jemr19040088
BibTeX
@article{Li2026,
author = {Li, Yanzhao and Li, Jin and Zhang, Xiaona and Liang, Hong},
title = {Uncertainty-Aware General Gaze Following via Circular Direction Distribution Learning and Probabilistic Gaze Geometry Modeling},
journal = {Journal of Eye Movement Research},
year = {2026},
volume = {19},
number = {4},
pages = {88},
doi = {10.3390/jemr19040088}
}
EUVIMED