Rights statement: © ACM, 2022. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in ETRA '22: 2022 Symposium on Eye Tracking Research and Applications https://dl.acm.org/doi/10.1145/3517031.3529642
Accepted author manuscript, 1.52 MB, PDF document
Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License
Final published version
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
}
TY - GEN
T1 - Real-time head-based deep-learning model for gaze probability regions in collaborative VR
AU - Bovo, Riccardo
AU - Giunchi, Daniele
AU - Sidenmark, Ludwig
AU - Costanza, Enrico
AU - Gellersen, Hans
AU - Heinis, Thomas
N1 - © ACM, 2022. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in ETRA '22: 2022 Symposium on Eye Tracking Research and Applications https://dl.acm.org/doi/10.1145/3517031.3529642
PY - 2022/6/11
Y1 - 2022/6/11
N2 - Eye behaviour has gained much interest in the VR research community as an interaction input and support for collaboration. Researchers implemented gaze inference models when eye-tracking is missing by using head behavior and saliency. However, these solutions are resource-demanding and thus unfit for untethered devices, and their angle accuracy is around 7°, which can be a problem in high-density informative areas. To address this issue, we propose a lightweight deep learning model that generates the probability density function of the gaze as a percentile contour. This solution allows us to introduce a visual attention representation based on a region rather than a point and manage a trade-off between the ambiguity of a region and the error of a point. We tested our model in untethered devices with real-time performances; we evaluated its accuracy which outperforms our identified baselines (average fixation map and head direction).
AB - Eye behaviour has gained much interest in the VR research community as an interaction input and support for collaboration. Researchers implemented gaze inference models when eye-tracking is missing by using head behavior and saliency. However, these solutions are resource-demanding and thus unfit for untethered devices, and their angle accuracy is around 7°, which can be a problem in high-density informative areas. To address this issue, we propose a lightweight deep learning model that generates the probability density function of the gaze as a percentile contour. This solution allows us to introduce a visual attention representation based on a region rather than a point and manage a trade-off between the ambiguity of a region and the error of a point. We tested our model in untethered devices with real-time performances; we evaluated its accuracy which outperforms our identified baselines (average fixation map and head direction).
KW - Neural networks
KW - Visual attention
KW - Gaze inference
KW - Gaze prediction
U2 - 10.1145/3517031.3529642
DO - 10.1145/3517031.3529642
M3 - Conference contribution/Paper
BT - ACM Symposium on Eye Tracking Research and Applications
PB - ACM
CY - New York
T2 - ETRA '22: 2022 Symposium on Eye Tracking Research and Applications
Y2 - 8 June 2022 through 11 June 2022
ER -