Institution profile

Darmstadt University of Applied Sciences

Academic institutioneurope · de
Official website
Research library31linked papers
Opportunities0open roles
Selected work

Representative Papers

Consumer-grade EEG-based Eye Tracking

Mar 18, 2025

Progress in consumer-grade electroencephalography–eye-tracking (EEG-ET) research has been hindered by the scarcity of high-quality, time-synchronized multimodal data. Method: This work introduces and publicly releases the first large-scale, multi-paradigm, standardized benchmark dataset for consumer-grade EEG-ET synchronization. It comprises 113 participants, 116 sessions, and 11.75 hours of high-fidelity synchronized recordings—acquired using low-cost commercial EEG systems (e.g., OpenBCI) and webcam-based eye trackers—spanning four oculomotor paradigms: saccades, smooth pursuit, fixation, and free viewing. All data undergo rigorous temporal alignment, bandpass filtering, and missing-value imputation; accompanying open-source preprocessing and analysis code is provided. Contribution/Results: The dataset substantially lowers hardware barriers for EEG-ET research, enhances reproducibility, and provides critical empirical support for gaze decoding under challenging conditions—including low-light environments and camera-free settings.

1 citationsRead paper

Towards Zero-Shot Domain Generalization for ID Cards Presentation Attack Detection

Aug 17, 2026

This study addresses the cross-national generalization challenge in identity document attack detection caused by the scarcity of real-world samples. We propose a few-shot/zero-shot detection framework based on prototypical networks and episodic training. Utilizing an EfficientNet-V2-b0 backbone, the method incorporates a four-sample prototypical head and a fixed-class variable-domain training mechanism to effectively learn universal attack cues and mitigate domain shift. Experiments demonstrate that the model achieves an average Equal Error Rate (EER) of approximately 9% across multi-national datasets and DLC-2021, significantly outperforming Softmax and CLIP baselines. These results indicate that the proposed approach provides an efficient and reliable solution for privacy-preserving cross-border remote account opening, effectively overcoming data limitations in diverse geographical contexts.

0 citationsRead paper
Recent publications

Latest Papers

Towards Zero-Shot Domain Generalization for ID Cards Presentation Attack Detection

Aug 17, 2026

This study addresses the cross-national generalization challenge in identity document attack detection caused by the scarcity of real-world samples. We propose a few-shot/zero-shot detection framework based on prototypical networks and episodic training. Utilizing an EfficientNet-V2-b0 backbone, the method incorporates a four-sample prototypical head and a fixed-class variable-domain training mechanism to effectively learn universal attack cues and mitigate domain shift. Experiments demonstrate that the model achieves an average Equal Error Rate (EER) of approximately 9% across multi-national datasets and DLC-2021, significantly outperforming Softmax and CLIP baselines. These results indicate that the proposed approach provides an efficient and reliable solution for privacy-preserving cross-border remote account opening, effectively overcoming data limitations in diverse geographical contexts.

0 citationsRead paper

MPISuperRes-PnP: A Super-Resolution Zero-Shot Plug-and-Play Reconstruction Algorithm for Magnetic Particle Imaging

Aug 10, 2026

This work addresses the low spatial resolution of magnetic particle imaging (MPI) reconstructions, a limitation inadequately tackled by existing super-resolution methods that either rely on training data or employ simplistic interpolation, often compromising detail recovery and generalization. The authors propose a zero-shot super-resolution MPI reconstruction method that integrates super-resolution directly into an energy minimization framework, leveraging a pre-trained Gaussian denoiser via a plug-and-play strategy—eliminating the need for additional training data. This approach represents the first zero-shot, training-free super-resolution technique for MPI, effectively enhancing spatial resolution while avoiding hallucinatory artifacts. The framework is inherently generalizable, accommodating diverse regularizers and imaging tasks. Experimental results demonstrate consistent and significant improvements in reconstruction quality on both synthetic and real MPI data, underscoring its practicality and robustness.

0 citationsRead paper