Projects, Grants and Cooperations

COMPOSITO Arthistoric Analysis of Architecture via Computer Vision (2013-2015) Inovation Fund FRONTIER, Heidelberg University funded by German Research Foundation (DFG) Reconstructing the correspondence between early modern facades and there self-similarity by means of weakly supervised learning
Objects in Mirror are Closer than they Appear Objectrecognition and Automatic Comparision of the Sachsenspiegel Codices (2012-2015)
Program for assistant Professors, Ministry of Science, Research and Art (MWK), Baden-Württemberg The stylistic and semantic changes of four dependent illumination cycles are analysed by automatic mapping and art historic interpretation
Artistic and Artifical Seeing Computer Vision and Art History in Methodical and Practical Cooperation (2013-2016) WIN-Kolleg funded by the Heidelberg Academy of Sciences and Humanities (HAW) A dialogue about artistic recognition and similarity as well as casestudies in a wide range of artisic production should combine the two fields in the context of Computational Humanities
Passion Search A sub-project of "Artistic and Artificial Seeing" WIN-Kolleg funded by the Heidelberg Academy of Sciences and Humanities (HAW) An unrestricted image search of the crucifixion using the Prometheus Image Archive (Cologne)
Video Parsing for Abnormality Detection Spatio-/Temporal Graphical Models and Applications in Image Analysis grant GRK 1653 funded by the German Research Foundation (DFG) Video parsing method for joint detection and localization of objects in video and recognition of abnormal instances among them
Computer-Assisted Detection and Analysis of Medieval Legal Gestures Realising the Potential of a Comprehensive University (2010-2012) Inovation Fund FRONTIER, Heidelberg University funded by German Research Foundation (DFG) The interdisciplinary Frontier project between computer vision and art history analyses the visual codes and artistic representation of embodied communication in medieval culture

Further Projects funded by the DFG in the Context of the Excellence Initiative

Voting by Grouping Dependent Parts
Beyond Straight Lines - Object Detection Using Curvature
Contour-based Object Detection
Max-Margin Regularization for Chamfer Matching
Visual Recognition using Embedded Feature Selection for Curvature Self-Similarity
From Meaningful Contours to Discriminative Object Shape
Drawing Process Reconstruction in Medieval Images
Visual object recognition in datasets of pre-modern images

Publications and more on our research can be found here.