Search our Publications
Latest Publications
Marvin Struwe, Stephan Hasler, Ute Bauer-Wersing , "A Two-stage Classifier Architecture for Detecting Objects under Real-world Occlusion Patterns", International Conference on Artificial Neural Networks ICANN 2014 , 2014.
AbstractDespite extensive efforts, state-of-the-art detection approaches show a strong degradation of performance with increasing level of occlusion. In this paper we investigate a strategy to improve the detection of occluded objects based on the analytic feature framework from \cite{struwe13} and compare the results in a car detection task. Motivated by an analysis of annotated traffic scenes we focus on a general concept to handle vertical occlus...
Download Bibtex file
Lydia Fischer, Barbara Hammer, Heiko Wersing , "Local Rejection Strategies for Learning Vector Quantization", Artificial Neural Networks and Machine Learning - ICANN 2014 - 24th International Conference on Artificial Neural Networks, vol. 8681, pp. 563-570, 2014.
AbstractClassi cation with rejection is well understood for classi ers which provide explicit class probabilities. The situation is more complicated for popular deterministic classi ers such as learning vector quantisation schemes: albeit reject options using simple distance-based geometric measures were proposed [4], their local scaling behaviour is unclear for complex problems. Here, we propose a local threshold selection strategy which automatic...
Download Bibtex file
Andreas Knoblauch, Edgar Körner, Ursula Körner, Friedrich Sommer , "Structural synaptic plasticity can explain graded amnesia, catastrophic forgetting, and the spacing effect", PLOS-ONE, 2014.
AbstractAlthough already William James and, more explicitly, Donald Hebb’s theory of cell assemblies have suggested that activity-dependent rewiring of neuronal networks is the substrate of learning and memory, over the last six decades most theoretical work on memory has focused on plasticity of existing synapses in prewired networks. Research in the last decade has emphasized that structural modification of synaptic connectivity is common in the adult ...
Download Bibtex file
Günther Palm, Andreas Knoblauch, Florian Hauser, Almut Schüz , "Cell assemblies in the cerebral cortex", Biological Cybernetics, 2014.
AbstractDonald Hebb’s concept of cell assemblies is a physiology-based idea for a distributed neural representation of behaviorally relevant objects, concepts, or constellations. In the late 70s Valentino Braitenberg started the endeavor to spell out the hypothesis that the cerebral cortex is the structure where cell assemblies are formed, maintained and used, in terms of neuroanatomy (which was his main concern) and also neurophysio...
Download Bibtex file
Thomas Guthier, Volker Willert, Julian Eggert , "Beyond Histograms: Why Learned Structure-Preserving Descriptors Outperform Statistical Features", European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN) 2014, 2014.
AbstractStatistical image descriptors based on histograms~\cite{lowe2004distinctive,dalal2006} are widely used in image processing, because they are fast and simple methods with high classification performance. However, they discard the local topological structure and thus lose descriminative information contained in the image. We show that features based on the simple cell/complex cell response of learned structure-preserving patterns outperform the sta...
Download Bibtex file
Julian Eggert , "Generalized Risk Estimation for intelligent ADAS Functions", IEEE Conference on Intelligent Transportation Systems (ITSC), pp. 711 - 718, 2014.
AbstractThe estimation of risk is a central cornerstone in the evaluation of traffic scene situations for intelligent ADAS. This applies to all levels of functions ranging from simple advices and warning functions right down to the evaluation of possible behavior alternatives, planning and autonomous driving. Current risk handling includes probabilistic collision measures, behavior planning using spatial and temporal occupancy grids, and time metrics suc...
Download Bibtex file
Florian Damerow and Julian Eggert , "Predictive risk maps", IEEE Conference on Intelligent Transportation Systems, pp. 703 - 710, 2014.
AbstractRisk evaluation schemes in urban environments have been developed for many traffic situations such as lane keeping or crossings to validate possible trajectories. Recent methods show difficulties for a high number of scene entities, as it is the case for many inner city scenarios. In this paper we address the problem of risk evaluation for motion planning in fast changing traffic situations with high variability. The presented risk evaluati...
Download Bibtex file
Christian Vollmer, Sven Hellbach, Julian Eggert, Horst-Michael Groß , "Sparse Coding of Human Motion Trajectories with Non-negative Matrix Factorization", Neurocomputing, pp. 22-32, 2014.
AbstractWe use shift-invariant Non-negative Matrix Factorization (NMF) for decom- posing continuous-valued time series into a number of characteristic primi- tives, i.e. the basis vectors, and their activations, which results in a model- independent and fully data driven parts-based representation. We interpret the basis vectors as short parts of motion that are shared between all trajec- tories in the data set, and the activations as onset times of...
Download Bibtex file
Christian Seegelke , "Cognitive Planning in Manual Action", University of Bielefeld, 2014.
AbstractMany of our daily activities require that we physically interact with one or more objects. Given that there is an infinite number of possible ways to achieve any given task, a core question in motor control is how particular actions for object manipulation are chosen. Previous research has demonstrated that the way people grasp objects is strongly influenced by future task demands or the intended action goal of the task. Anticipatory grasp postur...
Download Bibtex file Per Mail Request
Nikola Aulig, Emily Nutwell, Stefan Menzel, Duane Detwiler , "Towards Multi-objective Topology Optimization of Structures subject to Crash and Static Load Cases", Engineering Optimization 2014, pp. 847-852, 2014.
AbstractIn the optimization of automotive lightweight structures, typical requirements include stiffness and crashworthiness. The hybrid-cellular automata (HCA) algorithm is a heuristic topology optimization approach, which targets a uniform distribution of the internal energy density in the structure. It has been applied to the topology optimization of structures subject to crash or static loads. Multiple load cases can be considered by a linear weighti...
Download Bibtex file
1 ... 103 104 105 106 107 108 ... 183
Follow us
