50 citations · 60 across the 9 of their papers we have counts for
16 papers
Deconfounding Imitation Learning with Variational Inference
Risto Vuorio, Pim de Haan, Johann Brehmer +3
Standard imitation learning can fail when the expert demonstrators have different sensory inputs than the imitating agent. This is because partial observability gives rise to hidde…
Spatial-Temporal Transformer for Dynamic Scene Graph Generation
Yuren Cong, Wentong Liao, Hanno Ackermann +2
Dynamic scene graph generation aims at generating a scene graph of the given video. Compared to the task of scene graph generation from images, it is more challenging because of th…
Cuboids Revisited: Learning Robust 3D Shape Fitting to Single RGB Images
Florian Kluger, Hanno Ackermann, Eric Brachmann +2
Humans perceive and construct the surrounding world as an arrangement of simple parametric models. In particular, man-made environments commonly consist of volumetric primitives su…
NODIS: Neural Ordinary Differential Scene Understanding
Cong Yuren, Hanno Ackermann, Wentong Liao +2
Semantic image understanding is a challenging topic in computer vision. It requires to detect all objects in an image, but also to identify all the relations between them. Detected…
CONSAC: Robust Multi-Model Fitting by Conditional Sample Consensus
Florian Kluger, Eric Brachmann, Hanno Ackermann +3
We present a robust estimator for fitting multiple parametric models of the same form to noisy measurements. Applications include finding multiple vanishing points in man-made scen…
Learning Disentangled Representations via Independent Subspaces
Maren Awiszus, Hanno Ackermann, Bodo Rosenhahn
Image generating neural networks are mostly viewed as black boxes, where any change in the input can have a number of globally effective changes on the output. In this work, we pro…