2 papers
cs.AI2024
Towards Probabilistic Inductive Logic Programming with Neurosymbolic Inference and Relaxation
Fieke Hillerstrom, Gertjan Burghouts
Many inductive logic programming (ILP) methods are incapable of learning programs from probabilistic background knowledge, e.g. coming from sensory data or neural networks with pro…
cs.LG2021
Spot What Matters: Learning Context Using Graph Convolutional Networks for Weakly-Supervised Action Detection
Michail Tsiaousis, Gertjan Burghouts, Fieke Hillerström +1
The dominant paradigm in spatiotemporal action detection is to classify actions using spatiotemporal features learned by 2D or 3D Convolutional Networks. We argue that several acti…