31 citations · 58 across the 10 of their papers we have counts for
15 papers
Comparing object recognition in humans and deep convolutional neural networks -- An eye tracking study
Leonard E. van Dyck, Roland Kwitt, Sebastian J. Denzler +1
Deep convolutional neural networks (DCNNs) and the ventral visual pathway share vast architectural and functional similarities in visual challenges such as object recognition. Rece…
Topological Attention for Time Series Forecasting
Sebastian Zeng, Florian Graf, Christoph Hofer +1
The problem of (point) forecasting time series is considered. Most approaches, ranging from traditional statistical methods to recent learning-based techniq…
ICON: Learning Regular Maps Through Inverse Consistency
Hastings Greer, Roland Kwitt, Francois-Xavier Vialard +1
Learning maps between data samples is fundamental. Applications range from representation learning, image translation and generative modeling, to the estimation of spatial deformat…
Sparse Pose Trajectory Completion
Bo Liu, Mandar Dixit, Roland Kwitt +2
We propose a method to learn, even using a dataset where objects appear only in sparsely sampled views (e.g. Pix3D), the ability to synthesize a pose trajectory for an arbitrary re…
A Shooting Formulation of Deep Learning
François-Xavier Vialard, Roland Kwitt, Susan Wei +1
Continuous-depth neural networks can be viewed as deep limits of discrete neural networks whose dynamics resemble a discretization of an ordinary differential equation (ODE). Altho…
Deep Multi-View Learning via Task-Optimal CCA
Heather D. Couture, Roland Kwitt, J. S. Marron +3
Canonical Correlation Analysis (CCA) is widely used for multimodal data analysis and, more recently, for discriminative tasks such as multi-view learning; however, it makes no use…