Plant Classification from Bat-Like Echolocation Signals (2008)
Yovel, Y., Franz, M.O., Stilz, P.
Classification of plants according to their echoes is an elementary component of bat behavior that plays an important role in spatial orientation and food acquisition. Vegetation echoes are, however,...
A Nonparametric Approach to Bottom-Up Visual Saliency (2007)
Kienzle, W., Wichmann, F.A., Schölkopf, B., Franz, M.O.
This paper addresses the bottom-up influence of local image information on human eye movements. Most existing computational models use a set of biologically plausible linear filters, e.g., Gabor or...
Kienzle, W., Schölkopf, B., Wichmann, F., Franz, M.O.
Interest point detection in still images is a well-studied topic in computer vision. In the spatiotemporal domain, however, it is still unclear which features indicate useful interest points. In this...
Learning High-Order MRF Priors of Color Images (2006)
McAuley, J., Caetano, T., Smola, A., Franz, M.O.
In this paper, we use large neighborhood Markov random fields to learn rich prior models of color images. Our approach extends the monochromatic Fields of Experts model (Roth and Blackwell, 2005} to...
A Nonparametric Approach to Bottom-Up Visual Saliency (2006)
Kienzle, W., Wichmann, F.A., Schölkopf, B., Franz, M.O.
This paper addresses the bottom-up influence of local image information on human eye movements. Most existing computational models use a set of biologically plausible linear filters, e.g., Gabor or...
Learning an Interest Operator from Human Eye Movements (2006)
Kienzle, W., Wichmann, F.A., Schölkopf, B., Franz, M.O.
We present an approach for designing interest operators that are based on human eye movement statistics. In contrast to existing methods which use hand-crafted saliency measures, we use machine...
A unifying view of Wiener and Volterra theory and polynomial kernel regression (2006)
Volterra and Wiener series are perhaps the best understood nonlinear system representations in signal processing. Although both approaches have enjoyed a certain popularity in the past, their...
Implicit Wiener series for higher-order image analysis (2005)
Franz, M.O., Schölkopf, B., Saul, L.K., Weiss, Y., Bottou, L.
The computation of classical higher-order statistics such as higher-order moments or spectra is difficult for images due to the huge number of terms to be estimated and interpreted. We propose an...
Learning Depth From Stereo (2004)
Sinz,F., Quiñonero-Candela,J., Bakir,G.H., Rasmussen,C.E., Franz,M.O.
We compare two approaches to the problem of estimating the depth of a point in space from observing its image position in two different cameras: 1.~The classical photogrammetric approach explicitly...
Kernel Hebbian Algorithm for single-frame super-resolution (2004)
Kim,K.I., Franz,M.O., Schölkopf,B.
This paper presents a method for single-frame image super-resolution using an unsupervised learning technique. The required prior knowledge about the high-resolution images is obtained from Kernel...
Efficient Approximations for Support Vector Machines in Object Detection (2004)
Kienzle,W., Bakir,G.H., Franz,M.O., Schölkopf,B.
We present a new approximation scheme for support vector decision functions in object detection. In the present approach we are building on an existing algorithm where the set of support vectors is...
Semi-supervised kernel regression using whitened function classes (2004)
Franz,M.O., Kwon,Y., Rasmussen,C.E., Schölkopf,B.
The use of non-orthonormal basis functions in ridge regression leads to an often undesired non-isotropic prior in function space. In this study, we investigate an alternative regularization technique...
Implicit estimation of Wiener series (2004)
The Wiener series is one of the standard methods to systematically characterize the nonlinearity of a system. The classical estimation method of the expansion coefficients via cross-correlation...
Multivariate Regression via Stiefel Manifold Constraints (2004)
Bakir,G.H., Gretton,A., Franz,M.O., Schölkopf,B.
We introduce a learning technique for regression between high-dimensional spaces. Standard methods typically reduce this task to many one-dimensional problems, with each output dimension considered...
Insect-inspired estimation of egomotion (2004)
Franz,M.O., Chahl,J.S., Krapp,H.G.
Tangential neurons in the fly brain are sensitive to the typical optic flow patterns generated during egomotion. In this study, we examine whether a simplified linear model based on the organization...
Learning Depth From Stereo (2004)
Sinz, F., Quiñonero-Candela, J., Bakir, G.H., Rasmussen, C.E., Franz, M.O., Rasmussen, C. E., ...
We compare two approaches to the problem of estimating the depth of a point in space from observing its image position in two different cameras: 1.~The classical photogrammetric approach explicitly...
Kernel Hebbian Algorithm for single-frame super-resolution (2004)
Kim, K.I., Franz, M.O., Schölkopf, B., Leonardis, A., Bischof, H.
This paper presents a method for single-frame image super-resolution using an unsupervised learning technique. The required prior knowledge about the high-resolution images is obtained from Kernel...
Efficient Approximations for Support Vector Machines in Object Detection (2004)
Kienzle, W., Bakir, G.H., Franz, M.O., Schölkopf, B., Rasmussen, C. E., Bülthoff, H. H., ...
We present a new approximation scheme for support vector decision functions in object detection. In the present approach we are building on an existing algorithm where the set of support vectors is...
Semi-supervised kernel regression using whitened function classes (2004)
Franz, M.O., Kwon, Y., Rasmussen, C.E., Schölkopf, B., Rasmussen, C. E., Bülthoff, H. H., ...
The use of non-orthonormal basis functions in ridge regression leads to an often undesired non-isotropic prior in function space. In this study, we investigate an alternative regularization technique...
Implicit estimation of Wiener series (2004)
Franz, M.O., Schölkopf, B., Barros, A., Principe, J., Larsen, J., Adali, T., ...
The Wiener series is one of the standard methods to systematically characterize the nonlinearity of a system. The classical estimation method of the expansion coefficients via cross-correlation...
Multivariate Regression via Stiefel Manifold Constraints (2004)
Bakir, G.H., Gretton, A., Franz, M.O., Schölkopf, B., Rasmussen, C. E., Bülthoff, H. H., ...
We introduce a learning technique for regression between high-dimensional spaces. Standard methods typically reduce this task to many one-dimensional problems, with each output dimension considered...
Insect-inspired estimation of egomotion (2004)
Franz, M.O., Chahl, J.S., Krapp, H.G.
Tangential neurons in the fly brain are sensitive to the typical optic flow patterns generated during egomotion. In this study, we examine whether a simplified linear model based on the organization...
W. Ilg, G. H. Bakır, M. O. Franz, M. A. Giese
Imitation learning is a promising technique for teaching robots complex movement sequences. One key problem in this area is the transfer of perceived movement characteristics from perception to...
P. V. Gehler, P. V. Gehler, M. O. Franz, M. O. Franz
Abstract. Classical Volterra and Wiener theory of nonlinear systems does not address the problem of noisy measurements in system identification. This issue is treated in the present part of the...
Insect-Inspired Estimation of Self-Motion (2002)
The tangential neurons in the fly brain are sensitive to the typical optic flow patterns generated during self-motion. In this study, we examine whether a simplified linear model of these neurons can...
Insect-Inspired Estimation of Self-Motion (2002)
Franz, M.O., Chahl, J.S., Bülthoff, H. H., Poggio, T. A., Wallraven, C.
The tangential neurons in the fly brain are sensitive to the typical optic flow patterns generated during self-motion. In this study, we examine whether a simplified linear model of these neurons can...