7 papers
Static in Frames, Dynamic in Events: Rethinking Features in Event Cameras as Motion Cues
Hesam Araghi, Jan van Gemert, Nergis Tomen
Event cameras capture intensity changes asynchronously with high temporal resolution, requiring novel preprocessing methods for downstream tasks. Unlike static intensity snapshots,…
Rare-Aware Autoencoding: Reconstructing Spatially Imbalanced Data
Alejandro Castañeda Garcia, Jan van Gemert, Daan Brinks +1
Autoencoders can be challenged by spatially non-uniform sampling of image content. This is common in medical imaging, biology, and physics, where informative patterns occur rarely…
Data-Efficient Challenges in Visual Inductive Priors: A Retrospective
Robert-Jan Bruintjes, Attila Lengyel, Osman Semih Kayhan +4
Deep Learning requires large amounts of data to train models that work well. In data-deficient settings, performance can be degraded. We investigate which Deep Learning methods ben…
Making Every Event Count: Balancing Data Efficiency and Accuracy in Event Camera Subsampling
Hesam Araghi, Jan van Gemert, Nergis Tomen
Event cameras offer high temporal resolution and power efficiency, making them well-suited for edge AI applications. However, their high event rates present challenges for data tra…
Deep activity propagation via weight initialization in spiking neural networks
Aurora Micheli, Olaf Booij, Jan van Gemert +1
Spiking Neural Networks (SNNs) and neuromorphic computing offer bio-inspired advantages such as sparsity and ultra-low power consumption, providing a promising alternative to conve…
Learning Physics From Video: Unsupervised Physical Parameter Estimation for Continuous Dynamical Systems
Alejandro Castañeda Garcia, Jan van Gemert, Daan Brinks +1
Extracting physical dynamical system parameters from recorded observations is key in natural science. Current methods for automatic parameter estimation from video train supervised…