3 papers
cs.CV2025
Latent Uncertainty Representations for Video-based Driver Action and Intention Recognition
Koen Vellenga, H. Joe Steinhauer, Jonas Andersson +1
Deep neural networks (DNNs) are increasingly applied to safety-critical tasks in resource-constrained environments, such as video-based driver action and intention recognition. Whi…
cs.LG2025
Last Layer Hamiltonian Monte Carlo
Koen Vellenga, H. Joe Steinhauer, Göran Falkman +2
We explore the use of Hamiltonian Monte Carlo (HMC) sampling as a probabilistic last layer approach for deep neural networks (DNNs). While HMC is widely regarded as a gold standard…
cs.LG2024
Designing deep neural networks for driver intention recognition
Koen Vellenga, H. Joe Steinhauer, Alexander Karlsson +3
Driver intention recognition studies increasingly rely on deep neural networks. Deep neural networks have achieved top performance for many different tasks, but it is not a common…