Scene-Conditioned General Gaze Following in Static Images with Uncertainty-Preserving Geometry
Journal of Eye Movement Research · 04.11.2026 · 19 (6) · 126
DOI: 10.3390/jemr19060126 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Eye Movement Research, online erschienen am 04.11.2026. Verfasst von Yanzhao Li und 3 weiteren Autor:innen. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Given a static image and a selected person, general gaze following predicts the person’s likely gaze target. Ambiguous head cues can leave several geometrically plausible targets. We develop a scene-conditioned localization framework that retains directional uncertainty instead of collapsing it into one gaze direction. Building on a fixed, previously published geometry-guided reference, Distribution-Guided Query Interaction (DGQI) refines direction–distance candidates using scene evidence, the Distribution-Conditioned Localization Decoder (DCLD) adjusts the reference heatmap through residual prediction, and Selective Teacher-Margin Ranking Preservation (STMRP) protects selected correct spatial rankings during training. On the GazeFollow official test set, the final model reaches a pooled/global AUC of 0.9190, an original-resolution per-image AUC of 0.9342, and a normalized distance error of 0.1289 compared to the published baseline values of 0.9066, 0.9214, and 0.1423, respectively. Within-reference controls distinguish module effects from cross-generation changes in the scene backbone. DCLD yields the clearest localization gains; DGQI contributes a smaller discrimination gain; and STMRP improves per-image AUC at a localization cost. This separation has revealed that discrimination and peak localization need not improve together. Zero-shot experiments on VideoAttentionTarget and a coverage-limited ChildPlay subset expose further domain sensitivity. These results motivate protocol-aware, multi-metric evaluation of gaze predictions.
Zitieren
APA
Li, Y., Zhang, X., Liang, H., & Li, J. (2026). Scene-Conditioned General Gaze Following in Static Images with Uncertainty-Preserving Geometry. Journal of Eye Movement Research, 19(6), 126. https://doi.org/10.3390/jemr19060126
Vancouver
Li Y, Zhang X, Liang H, Li J. Scene-Conditioned General Gaze Following in Static Images with Uncertainty-Preserving Geometry. Journal of Eye Movement Research. 2026;19(6):126. doi:10.3390/jemr19060126
BibTeX
@article{Li2026,
author = {Li, Yanzhao and Zhang, Xiaona and Liang, Hong and Li, Jin},
title = {Scene-Conditioned General Gaze Following in Static Images with Uncertainty-Preserving Geometry},
journal = {Journal of Eye Movement Research},
year = {2026},
volume = {19},
number = {6},
pages = {126},
doi = {10.3390/jemr19060126}
}
EUVIMED