7 papers
Simplified Cross-Modal Calibration for Heterogeneous Event-RGB Stereo Systems
Nico Hessenthaler, Adam T. Müller, Nicolaj C. Stache
Accurate extrinsic calibration between event-based and frame-based cameras remains a practical bottleneck for heterogeneous stereo systems. Existing approaches often require sensor…
Drifting Models for Surrogate Flow Modeling
Chris R. Jung, Markus Dörr, Natalie Jüngling +3
While Computational Fluid Dynamics (CFD) provides high-fidelity flow fields for optimizing indoor environments, its computational cost limits rapid exploration. To solve this probl…
Reducing Experimental Testing in Space Propulsion Film Cooling Analyses by Pixelwise Generative Image Interpolation
Adam T. Müller, Philipp J. Teuffel, Konstantin Manassis +1
We propose a machine learning approach for image regression from sparse experimental measurements. We show the application of the proposed method on film cooling studies in propuls…
Generative Anonymization in Event Streams
Adam T. Müller, Mihai Kocsis, Nicolaj C. Stache
Neuromorphic vision sensors offer low latency and high dynamic range, but their deployment in public spaces raises severe data protection concerns. Recent Event-to-Video (E2V) mode…
Monte Carlo Stochastic Depth for Uncertainty Estimation in Deep Learning
Adam T. Müller, Tobias Rögelein, Nicolaj C. Stache
The deployment of deep neural networks in safety-critical systems necessitates reliable and efficient uncertainty quantification (UQ). A practical and widespread strategy for UQ is…
Sign Segmentation with Changepoint-Modulated Pseudo-Labelling
Katrin Renz, Nicolaj C. Stache, Neil Fox +2
The objective of this work is to find temporal boundaries between signs in continuous sign language. Motivated by the paucity of annotation available for this task, we propose a si…
Sign language segmentation with temporal convolutional networks
Katrin Renz, Nicolaj C. Stache, Samuel Albanie +1
The objective of this work is to determine the location of temporal boundaries between signs in continuous sign language videos. Our approach employs 3D convolutional neural networ…