Computational models of the human visual field account for head, neck, and eye movements to calculate fixation likelihood
Recent computational models of gaze and visual attention incorporate head, neck, and body movements alongside eye tracking to accurately predict fixation likelihood and gaze trajectories in dynamic environments.
Multiple recent papers ([1], [3], [5], [7]) directly support the claim that computational models of the human visual field and gaze prediction integrate head, neck, and body movements alongside eye tracking to calculate fixation likelihood. The retrieved literature offers strong empirical and computational evidence confirming this multi-modal approach without any papers refuting the claim.
Zhiming Hu, Congyi Zhang, Sheng Li, Guoping Wang, Dinesh Manocha. SGaze: A Data-Driven Eye-Head Coordination Model for Realtime Gaze Prediction. 2019. https://doi.org/10.1109/TVCG.2019.2899187
SGaze develops a data-driven eye-head coordination model for realtime gaze prediction by evaluating linear correlations between gaze positions and head rotation angular velocities.
See more details
Zhiming Hu, Jiahui Xu, Syn Schmitt, Andreas Bulling. Pose2Gaze: Eye-Body Coordination During Daily Activities for Gaze Prediction From Full-Body Poses. 2023. https://doi.org/10.1109/TVCG.2024.3412190
Pose2Gaze presents an eye-body coordination model that extracts features from head direction and full-body poses to accurately predict human eye gaze.
Lingling Chen, Yingxi Li, Xiaowei Bai, Xiaodong Wang, Yongqiang Hu, Mingwu Song, Liang Xie, Ye Yan, Erwei Yin. Real-time Gaze Tracking with Head-eye Coordination for Head-mounted Displays. 2022. https://doi.org/10.1109/ISMAR55827.2022.00022
HE-Tracker demonstrates a multi-modal network that fuses head-movement features with eye features to successfully regress gaze positions in AR head-mounted displays.
Colin Rubow, Chia-Hsuan Tsai, Erica Brewer, Connor Mattson, Daniel S. Brown, Haohan Zhang. A dataset of paired head and eye movements during visual tasks in virtual environments. 2024. https://doi.org/10.1038/s41597-024-04184-1
This dataset pairs head and eye movements during visual tasks in virtual environments to enable predictive models of intended head movement conditioned on gaze.
The paper trail · every fact has a biography
Challenge the receipt
Citation formatting by citeproc-js (Frank Bennett) and the Citation Style Language project. Source and licenses.
Terms · Privacy · How verdicts work · Dispute this receipt