• Publications
  • Influence
Classification of motor errors to provide real-time feedback for sports coaching in virtual reality - A case study in squats and Tai Chi pushes
TLDR
A novel pipeline to detect a trainee’s errors during exercise that is designed to automatically generate feedback for the trainee is proposed, showing its superiority over two popular approaches from human activity recognition applied to the problem, k-Nearest Neighbor combined with Dynamic Time Warping and Convolutional Neural Networks with a Long Short-term Memory Network. Expand
Mitigating Concept Drift via Rejection
TLDR
Two recent learning architectures for drift are extended, the self-adjusting memory architecture (SAM-kNN) and adaptive random forests (ARF), to incorporate a reject option, resulting in highly competitive state-of-the-art technologies. Expand
Interpretation of linear classifiers by means of feature relevance bounds
TLDR
This paper formalizes two interpretations of the all-relevant problem and proposes a polynomial method to approximate one of them for the important hypothesis class of linear classifiers, which also enables a distinction between strongly and weakly relevant features. Expand
Adversarial attacks hidden in plain sight
TLDR
A technique is composed that allows to hide adversarial attacks in regions of high complexity, such that they are imperceptible even to an astute observer with regards to human visual perception. Expand
Effects of variability in synthetic training data on convolutional neural networks for 3D head reconstruction
TLDR
A systematic analysis is performed in order to determine how the presence of different types of variability in the training data affects the generalization properties of the network for 3-dimensional head reconstruction. Expand
Adversarial Robustness Curves
TLDR
This work takes first steps towards separating robustness analysis from the choice of robustness threshold and norm, and proposes robustness curves as a more general view of the robustness behavior of a model and investigates under which circumstances they can qualitatively depend on the chosen norm. Expand
Ontology-based Extraction of Structured Information from Publications on Preclinical Experiments for Spinal Cord Injury Treatments
TLDR
A first prototype of an ontology-based information extraction system that automatically extracts relevant preclinical knowledge about spinal cord injury treatments from natural language text by recognizing participating entity classes and linking them to each other is described. Expand
SCIE: Information Extraction for Spinal Cord Injury Preclinical Experiments – A Webservice and Open Source Toolkit
TLDR
SCIE is an automated information extraction pipeline capable of detecting relevant information in SCI publications based on ontological entity and probabilistic relation detection and achieves an average extraction performance of 76 % precision and 52 % recall. Expand
How to compare adversarial robustness of classifiers from a global perspective
TLDR
It is shown that point-wise measures fail to capture important global properties that are essential to reliably compare the robustness of different classifiers, and new ways in which robustness curves can be used to systematically uncover these properties are introduced. Expand
Recovering Localized Adversarial Attacks
TLDR
This contribution quantitatively and qualitatively investigates the capability of three popular explainers of classifications – classic salience, guided backpropagation, and LIME – with respect to their ability to identify regions of attack as the explanatory regions for the (incorrect) prediction in representative examples from image classification. Expand
...
1
2
...