GazeHRNet: Head-Centric Spatial Encoding and Gaze-Aware Feature Interaction for Gaze Target Detection
Sensors · 28.07.2026 · 26 (15) · 4799
DOI: 10.3390/s26154799 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 28.07.2026. Verfasst von Tianxiang Nan und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Technology, China University of Petroleum (East China), Qingdao 266580, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Shandong Province, Excellent Young Scientists Fund of the Natural Science Foundation of Shandong Province.
Abstract (Originalsprache)
Gaze target detection requires understanding where a person is looking by jointly reasoning about the gazer and the surrounding scene. While recent methods have benefited from powerful pretrained visual backbones, they often treat gaze prediction as a generic localization problem and overlook a key property of the task: the target should be interpreted in relation to the person’s head. This limits their ability to model direction, distance, and head-scene dependencies in a unified manner. We propose GazeHRNet, a head-centric reasoning framework for RGB-based gaze target detection. Instead of relying on absolute image coordinates or auxiliary geometric inputs, GazeHRNet represents the scene from the gazer’s perspective through Head-Centric Polar Encoding and organizes visual features by their spatial relevance to the head via Head-Aware Attention Routing. It further combines coarse spatial reasoning with fine-grained anisotropic heatmap prediction, enabling reliable target localization under cluttered scenes and varying head positions. Experiments on GazeFollow and VideoAttentionTarget show that GazeHRNet achieves 0.952 and 0.929 AUC with L2 distances of 0.102 and 0.103, respectively, using only RGB input and 3 M trainable parameters. Cross-dataset evaluation further demonstrates improved robustness and generalization across different scenes and subject distributions.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Computer Science and Technology, China University of Petroleum (East China), Qingdao 266580, China.
ORCID-Profile: Tianxiang Nan, Zhi Li, Xinyu Liu
Förderung
- Natural Science Foundation of Shandong Province
- Excellent Young Scientists Fund of the Natural Science Foundation of Shandong Province
Zitieren
APA
Nan, T., Chen, C., Chen, X., Li, Z., Wei, X., & Liu, X. (2026). GazeHRNet: Head-Centric Spatial Encoding and Gaze-Aware Feature Interaction for Gaze Target Detection. Sensors, 26(15), 4799. https://doi.org/10.3390/s26154799
Vancouver
Nan T, Chen C, Chen X, Li Z, Wei X, Liu X. GazeHRNet: Head-Centric Spatial Encoding and Gaze-Aware Feature Interaction for Gaze Target Detection. Sensors. 2026;26(15):4799. doi:10.3390/s26154799
BibTeX
@article{Nan2026,
author = {Nan, Tianxiang and Chen, Chenglizhao and Chen, Xi and Li, Zhi and Wei, Xiangyu and Liu, Xinyu},
title = {GazeHRNet: Head-Centric Spatial Encoding and Gaze-Aware Feature Interaction for Gaze Target Detection},
journal = {Sensors},
year = {2026},
volume = {26},
number = {15},
pages = {4799},
doi = {10.3390/s26154799}
}
EUVIMED