Resource-efficient neural networks for mobile eye tracking

• Applicant: Dr. Wolfgang Fuhl
• Subject Area: Image and Language Processing, Computer Graphics and Visualisation, Human Computer Interaction, Ubiquitous and Wearable Computing
• Term: since 2023
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 508330921

The goal of this project is to address the research gaps 1) Specific dependency on CUDA 2) Limited porting to smartphones/tablets and 3) Annotations to eye-specific features in the RGB domain 4) Combinatorial layers in path-based networks in the state of the art through 1/2) the framework to be built 3) the annotation of already public datasets and the pre-trained models 4) Research in the area of learnable combinatorics of layers as well as the application of reduction techniques to path-based networks.

• DFG Programme: Research Grants