In this paper, we use fully convolutional neural networks for the semantic segmentation of eye tracking data. We also use these networks for reconstruction, and in conjunction with a …
In this paper we present a new approach for pupil segmentation. It can be computed and trained very efficiently, making it ideal for online use for high speed eye trackers as well as …
In this work, we inspect different data sources for browser fingerprints. We show which disadvantages and limitations browser statistics have and how this can be avoided with …
W Fuhl, E Kasneci - ACM Symposium on Eye Tracking Research and …, 2021 - dl.acm.org
We present a new dataset with annotated eye movements. The dataset consists of over 800,000 gaze points recorded during a car ride in the real world and in the simulator. In total …
In this paper we present GroupGaze. It is a tool that can be used to calculate the gaze direction and the gaze position of whole groups. GroupGazer calculates the gaze direction …
W Fuhl - arXiv preprint arXiv:2109.02345, 2021 - arxiv.org
In this work, we introduce pixel wise tensor normalization, which is inserted after rectifier linear units and, together with batch normalization, provides a significant improvement in the …
W Fuhl - arXiv preprint arXiv:2206.09697, 2022 - arxiv.org
In this report, we combine the idea of Wide ResNets and transfer learning to optimize the architecture of deep neural networks. The first improvement of the architecture is the use of …
W Fuhl, Y Rong, T Motz, M Scheidt… - 2020 25th …, 2021 - ieeexplore.ieee.org
We present a reformulation of the regression and classification, which aims to validate the result of a machine learning algorithm. Our reformulation simplifies the original problem and …
W Fuhl, E Jasneci - 2022 International Joint Conference on …, 2022 - ieeexplore.ieee.org
In this work, we present an alternative to conventional residual connections, which is inspired by maxout nets. This means that instead of the addition in residual connections, our …