Correlational Spectral Clustering (2008)
We present a new method for spectral clustering with paired data based on kernel canonical correlation analysis, called correlational spectral clustering. Paired data are common in real world data...
Learning to Localize Objects with Structured Output Regression (2008)
Blaschko, M.B., Lampert, C.H., Forsyth, D. A., Torr, P. H.S., Zisserman, A.
Sliding window classifiers are among the most successful and widely applied techniques for object localization. However, training is typically done in a way that is not specific to the localization...
Semi-Supervised Laplacian Regularization of Kernel Canonical Correlation Analysis (2008)
Blaschko, M.B., Lampert, C.H., Gretton, A., Daelemans, W., Goethals, B., Morik, K.
Kernel canonical correlation analysis (KCCA) is a dimensionality reduction technique for paired data. By finding directions that maximize correlation, KCCA learns representations that are more...
Partitioning of Image Datasets using Discriminative Context Information (2008)
We propose a new method to partition an unlabeled dataset, called Discriminative Context Partitioning (DCP). It is motivated by the idea of splitting the dataset based only on how well the resulting...
Beyond Sliding Windows: Object Localization by Efficient Subwindow Search (2008)
Lampert, C.H., Blaschko, M.B., Hofmann, T.
Most successful object recognition systems rely on binary classification, deciding only if an object is present or not, but not providing information on the actual object location. To perform...
Optimal Dominant Motion Estimation using Adaptive Search of Transformation Space (2007)
Ulges, A., Lampert, C.H., Keysers, D., Breuel, T.M.
The extraction of a parametric global motion from a motion field is a task with several applications in video processing. We present two probabilistic formulations of the problem and carry out...
An optimal nonorthogonal separation of the anisotropic Gaussian convolution filter (2006)
We give an analytical and geometrical treatment of what it means to separate a Gaussian kernel along arbitrary axes in R-n, and we present a separation scheme that allows us to efficiently implement...
An Optimal Non-Orthogonal Separation of the Anisotropic Gaussian Convolution Filter (2005)
We give an analytical and geometrical treatment of what it means to separate a Gaussian kernel along arbitrary axes in Rn, and we present a separation scheme that allows to efficiently implement...
Boundary regularity of admissible operators (2005)
In strictly pseudoconvex domains with smooth boundary, we prove a commutator relationship between admissible integral operators, as introduced by Lieb and Range, and smooth vector fields which are...