no code implementations • 23 Jan 2024 • Martin Skrodzki, Hunter van Geffen, Nicolas F. Chaves-de-Plaza, Thomas Höllt, Elmar Eisemann, Klaus Hildebrandt
The need to understand the structure of hierarchical or high-dimensional data is present in a variety of fields.
no code implementations • 29 Aug 2023 • Martin Skrodzki, Nicolas Chaves-de-Plaza, Klaus Hildebrandt, Thomas Höllt, Elmar Eisemann
Further, we show how this approach speeds up the computation and increases the quality of the embeddings.
1 code implementation • 28 Feb 2023 • Josua Sassen, Klaus Hildebrandt, Martin Rumpf, Benedikt Wirth
Parametrizations of data manifolds in shape spaces can be computed using the rich toolbox of Riemannian geometry.
no code implementations • 17 Oct 2022 • Nicolas F. Chaves-de-Plaza, Klaus Hildebrandt, Anna Vilanova
Post-translational modifications (PTMs) affecting a protein's residues (amino acids) can disturb its function, leading to illness.
1 code implementation • CVPR 2022 • Yancong Lin, Ruben Wiersma, Silvia L. Pintea, Klaus Hildebrandt, Elmar Eisemann, Jan C. van Gemert
Deep learning has improved vanishing point detection in images.
1 code implementation • 16 Nov 2021 • Ruben Wiersma, Ahmad Nasikun, Elmar Eisemann, Klaus Hildebrandt
Learning from 3D point-cloud data has rapidly gained momentum, motivated by the success of deep learning on images and the increased availability of 3D~data.
Ranked #6 on 3D Part Segmentation on ShapeNet-Part
1 code implementation • 1 Nov 2021 • Prerak Mody, Nicolas Chaves-de-Plaza, Klaus Hildebrandt, Rene van Egmond, Huib de Ridder, Marius Staring
However, in a QA context, a model should also have high uncertainty in inaccurate regions and low uncertainty in accurate regions.
1 code implementation • SIGGRAPH 2020 • Ruben Wiersma, Elmar Eisemann, Klaus Hildebrandt
We propose a network architecture for surfaces that consists of vector-valued, rotation-equivariant features.