GRK 1653:  Spatio/Temporal Probabilistic Graphical Models and Applications in Image Analysis

• Subject Area: Computer Science ; Mathematics
• Term: from 2010 to 2019
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 159280219

• Final Report Year: 2020

Final Report Abstract

Probabilistic graphical models provide a consistent framework for the statistical modeling and the computational analysis of scientific empirical data. The past decade has witnessed a significant increase in respecive research in the field of image analysis and related application areas, driven by thesynergy between statistics, pattern recognition, computer vision and machine learning. The objective is to devise models that enable to infer a coherent global interpretation of noise and ambiguous local image measurements, taking into account spatiotemporal context in images and videos, and domain-specific contextual knowledge. Applications of probabilistic graphical models to such large-scale problems raise numerous research problems of modeling and algorithm design for inference and learning, requiring interdisciplinary expertise in applied mathematics, computer science and physics, besides a profound knowledge of the respective application areas. The basic intention of the Research Training Group is to gather experts from these fields and to establish a coherent research and study program on probabilistic graphical models, with a focus on spatial and spatiotemporal models and their applications in image analysis. The project treats methodological basic research on an equal footing with challenging scientific applications of image analysis in environmental science, life sciences and industry. The Research Training Group will provide a scientifically unique environment for study, collaboration and innovative research on probabilistic graphical models across disciplines, producing highly-qualified candidates for research careers in academia and industry.

Publications

• (2010). „A Study of Parts-Based Object Class Detection Using Complete Graphs“. In: Int. J. Comp. Vision 87.1-2, S. 93–117
  Bergtholdt, M., J. H. Kappes, S. Schmidt und C. Schnörr
  
• (2010). „An Empirical Comparison of Inference Algorithms for Graphical Models with Higher Order Factors Using OpenGM“. In: Pattern Recognition, Proc. 32th DAGM Symposium
  Andres, B., J. H. Kappes, U. Köthe, C. Schnörr und F. Hamprecht
  
• (2011). „Bayesian inference for general Gaussian graphical models with application to multivariate lattice data“. In: Journal of the American Statistical Association 106, S. 1418–1433
  Dobra, A., A. Lenkoski und A. Rodriguez
  
• (2011). „DELTR: Digital Embryo Lineage Tree Reconstructor“. In: Eighth IEEE International Symposium on Biomedical Imaging (ISBI), S. 1557–1560
  Lou, X., F. Kaster, M. Lindner, B. Kausler, U. Köthe, B. Höckendorf, J. Wittbrodt, H. Jänicke und F. A. Hamprecht
  
• (2011). „Globally Optimal Image Partitioning by Multicuts“. In: EMMCVPR. Springer
  Kappes, J. H., M. Speth, B. Andres, G. Reinelt und C. Schnörr
  
• (2011). „Order Preserving and Shape Prior Constrained Intra- Retinal Layer Segmentation in Optical Coherence Tomography“. In: MICCAI. Hrsg. von G. Fichtinger, A. L. Martel und T. M. Peters. Bd. 6893. Lecture Notes in Computer Science. Springer, S. 370– 377
  Rathke, F., S. Schmidt und C. Schnörr
  
• (2011). „Probabilistic Image Segmentation with Closedness Constraints“. In: ICCV
  Andres, B., J. H. Kappes, T. Beier, U. Köthe und F. Hamprecht
  
• (2011). „Sparse covariance estimation in heterogeneous samples“. In: Electronic Journal of Statistics 5, S. 981–1014
  Rodriguez, A., A. Lenkoski und A. Dobra
  
• (2011). „Video parsing for abnormality detection“. In: IEEE International Conference on Computer Vision, ICCV, S. 2415–2422
  Antic, B. und B. Ommer
  
• (2012). „A Bayesian Approach to Spaceborn Hyperspectral Optical Flow Estimation on Dust Aerosols“. In: Proceedings of the International Geoscience and Remote Sensing Symposium, S. 256–259
  Bachl, F. E., P. Fieguth und C. S. Garbe
  
• (2012). „A Discrete Chain Graph Model for 3d+t Cell Tracking with High Misdetection Robustness“. In: ECCV
  Kausler, B. X., M. Schiegg, B. Andres, M. Lindner, U. Köthe, H. Leitte, J. Wittbrodt, L. Hufnagel und F. A. Hamprecht
  
• (2012). „Classifying and Tracking Dust Plumes from Passive Remote Sensing“. In: Proceedings of the ESA, SOLAS & EGU Joint Conference ‘Earth Observation for Ocean-Atmosphere Interaction Science’. Bd. 703. ESA Special Publication, S1–3
  Bachl, F. E. und C. S. Garbe
  
• (2012). „Multivariate Probabilistic Forecasting Using Ensemble Bayesian Model Averaging and Copulas“. In: Quarterly Journal of the Royal Meteorological Society 139.673, S. 982–991
  Möller, A., A. Lenkoski und T. Thorarinsdottir
  
• (2012). „Robust FDI Determinants“. In: Journal of Maroeconomics 34, S. 637–651
  Eicher, T. S., L. Helfman und A. Lenkoski
  
• (2012). „Robust Multiple-Instance Learning with Superbags“. In: Computer Vision - ACCV, Revised Selected Papers, Part II
  Antic, B. und B. Ommer
  
• (2012). „The Lazy Flipper: Efficient Depth-limited Exhaustive Search in Discrete Graphical Models“. In: ECCV
  Andres, B., J. H. Kappes, T. Beier, U. Köthe und F. Hamprecht
  
• (2013). „A Comparative Study of Modern Inference Techniques for Discrete Energy Minimization Problems“. In: IEEE Conference on Computer Vision and Pattern Recognition
  Kappes, J. H., B. Andres, F. A. Hamprecht, C. Schnörr, S. Nowozin, D. Batra, S. Kim, B. X. Kausler, J. Lellmann, N. Komodakis und C. Rother
  
• (2013). „A Hierarchical Approach to Optimal Transport“. In: Scale Space and Variational Methods (SSVM), S. 452–464
  Schmitzer, B. und C. Schnörr
  
• (2013). „Bayesian Inference on Integrated Continuity Fluid Flows and their Application to Dust Aerosols“. In: Proceedings of the International Geoscience and Remote Sensing Symposium, S. 2246– 2249
  Bachl, F. E., P. Fieguth und C. S. Garbe
  
• (2013). „Chapter Three - Zinc Finger Proteins and the 3D Organization of Chromosomes“. In: Organisation of Chromosomes. Hrsg. von R. Donev. Bd. 90. Advances in Protein Chemistry and Structural Biology. Academic Press, S. 67–117
  Feinauer, C. J., A. Hofmann, S. Goldt, L. Liu, G. Maté und D. W. Heermann
  
• (2013). „Graphical and Topological Analysis of the Cell Nucleus“. Diss. Faculty of Physics und Astronomy, Heidelberg University
  Maté, G.
  
• (2013). „Less Is More: Video Trimming for Action Recognition“. In: 2013 IEEE International Conference on Computer Vision Workshops
  Antic, B., T. Milbich und B. Ommer
  
• (2013). „Modelling convex shape priors and matching based on the Gromov-Wasserstein distance“. In: Journal of Mathematical Imaging and Vision 46.1, S. 143–159
  Schmitzer, B. und C. Schnörr
  
• (2013). „Object Segmentation by Shape Matching with Wasserstein Modes“. In: Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), S. 123–136
  Schmitzer, B. und C. Schnörr
  
• (2013). „Towards Efficient and Exact MAP- Inference for Large Scale Discrete Computer Vision Problems via Combinatorial Optimization“. In: CVPR
  Kappes, J. H., M. Speth, G. Reinelt und C. Schnörr
  
• (2013). „Tracking-by-Assignment as a Probabilistic Graphical Model with Applications in Developmental Biology“. Diss. Faculty of Physics und Astronomy
  Kausler, B.
  
• (2014). „A topological similarity measure for proteins“. In: Biochimica et Biophysica Acta (BBA) - Biomembranes 1838.4. Viral Membrane Proteins - Channels for Cellular Networking, S. 1180–1190
  Maté, G., A. Hofmann, N. Wenzel und D. W. Heermann
  
• (2014). „Exact Solutions for Discrete Graphical Models: Multicuts and Reduction Techniques“. Diss. Faculty of Mathematics und Computer Science, Heidelberg University
  Speth, M.
  
• (2014). „Isometry Invariant Shape Priors for Variational Image Segmentation“. Diss. Faculty of Mathematics und Computer Science, Heidelberg University
  Schmitzer, B.
  
• (2014). „Latent Structured Models for Video Understanding“. Diss. Faculty of Mathematics und Computer Science, Heidelberg University
  Antic, B.
  
• (2014). „Learning Latent Constituents for Recognition of Group Activities in Video“. In: Computer Vision - ECCV
  Antic, B. und B. Ommer
  
• (2014). „Modeling of Locally Scaled Spatial Point Processes, and Applications in Image Analysis“. Diss. Faculty of Mathematics und Computer Science, Heidelberg University
  Didden, E.-M.
  
• (2014). „Multivariate and Spatial Ensemble Postprocessing Methods“. Diss. Faculty of Mathematics und Computer Science, Heidelberg University
  Möller, A.
  
• (2014). „Persistence intervals of fractals“. In: Physica A: Statistical Mechanics and its Applications 405, S. 252–259
  Maté, G. und D. W. Heermann
  
• (2014). „Probabilistic Intra-Retinal Layer Segmentation in 3-D OCT Images Using Global Shape Regularization“. In: Medical Image Analysis 18.5, S. 781–794
  Rathke, F., S. Schmidt und C. Schnörr
  
• (2014). „Statistical analysis of protein ensembles“. In: Frontiers in Physics
  Maté, G. und D. W. Heermann
  
• (2014). „The affinely invariant distance correlation“. In: Bernoulli 20.4, S. 2305–2330
  Dueck, J., D. Edelmann, T. Gneiting und D. Richards
  
• (2014). „Two-Stage Bayesian Model Averaging in the Endogenous Variable Model“. In: Econometric Reviews 33, S. 122–151
  Lenkoski, A., T. S. Eicher und A. E. Raftery
  
• (2012). „Weakly Convex Coupling Continuous Cuts and Shape Priors“. In: Scale Space and Variational Methods (SSVM), S. 423–434
  Schmitzer, B. und C. Schnörr
  
• (2015). „A Comparative Study of Modern Inference Techniques for Structured Discrete Energy Minimization Problems“. In: International Journal of Computer Vision 115.2, S. 155–184
  Kappes, J. H., B. Andres, F. A. Hamprecht, C. Schnörr, S. Nowozin, D. Batra, S. Kim, B. X. Kausler, T. Kröger, J. Lellmann, N. Komodakis, B. Savchynskyy und C. Rother
  
• (2015). „A Computational Approach to Log-Concave Density Estimation“. In: An. St. Univ. Ovidius Constanta 23.3, S. 151–166
  Rathke, F. und C. Schnörr
  
• (2015). „A Convex Relaxation Approach to the Affine Subspace Clustering Problem“. In: Pattern Recognition - 37th German Conference, GCPR 2015, Aachen, Germany, October 7-10, 2015, Proceedings, S. 67–78
  Silvestri, F., G. Reinelt und C. Schnörr
  
• (2015). „A generalization of an integral arising in the theory of distance correlation“. In: Statistics & Probability Letters 97, S. 116–119
  Dueck, J., D. Edelmann und D. Richards
  
• (2015). „A generalized Potts model for confocal microscopy images“. In: Int. J. Modern Physics 29.8, S. 1550048
  Maté, G. und D. W. Heermann
  
• (2015). „Adaptive Dictionary-Based Spatio-Temporal Flow Estimation for Echo PIV“. In: Proc. EMMCVPR
  Bodnariuc, E., A. Gurung, S. Petra und C. Schnörr
  
• (2015). „Adaptive Sharpening of Multimodal Distributions“. In: Proc. CVCS. IEEE, S. 1–4
  Åström, F., M. Felsberg und H. Scharr
  
• (2015). „Bayesian Hierarchical Models for Remote Assessment of Atmospheric Dust“. Diss. Faculty of Mathematics und Computer Science
  Bachl, F. E.
  
• (2015). „Bayesian Motion Estimation for Dust Aerosols“. In: The Annals of Applied Statistics 9.3, S. 1298–1327
  Bachl, F. E., A. Lenkoski, T. L. Thorarinsdottir und C. S. Garbe
  
• (2015). „Dependencies in Complex Systems“. Diss. Faculty of Mathematics und Computer Science, Heidelberg University
  Dueck, J.
  
• (2015). „Estimating Vehicle Ego-Motion and Piecewise Planar Scene Structure from Optical Flow in a Continuous Framework“. In: German Conference on Pattern Recognition. Springer, S. 41–52
  Neufeld, A., J. Berger, F. Becker, F. Lenzen und C. Schnörr
  
• (2015). „Globally Optimal Joint Image Segmentation and Shape Matching based on Wasserstein Modes“. In: J. Math. Imag. Vision 52.3, S. 436–458
  Schmitzer, B. und C. Schnörr
  
• (2015). „Improving 3d em data segmentation by joint optimization over boundary evidence and biological priors“. In: International Symposium on Biomedical Imaging
  Krasowski, N., T. Beier, G. Knott, U. Koethe, F. Hamprecht und A. Kreshuk
  
• (2015). „On Coupled Regularization for Non-convex Variational Image Enhancement“. In: Proc. ACPR. IEEE, S. 786–790
  Åström, F. und C. Schnörr
  
• (2015). „Per-Sample Kernel Adaptation for Visual Recognition and Grouping“. In: 2015 IEEE International Conference on Computer Vision, ICCV
  Antic, B. und B. Ommer
  
• (2015). „Probabilistic Correlation Clustering and Image Partitioning Using Perturbed Multicuts“. In: Proc. SSVM. LNCS. Springer
  Kappes, J., P. Swoboda, B. Savchynskyy, T. Hazan und C. Schnörr
  
• (2015). „Probabilistic Graphical Models for Medical Image Segmentation“. Diss. Faculty of Mathematics und Computer Science, Heidelberg University
  Rathke, F.
  
• (2015). „Radiation Induced Chromatin Conformation Changes Analysed by Fluorescent Localization Microscopy, Statistical Physics, and Graph Theory“. In: PLOS One 10.6, e0128555
  Zhang, Y., G. Maté, P. Müller, S. Hillebrandt, M. Krufczik, M. Bach, R. Kaufmann, M. Hausmann und D. W. Heermann
  
• (2015). „Second Order Minimum Energy Filtering on SE(3) with Nonlinear Measurement Equations“. In: Scale Space and Variational Methods. Springer, S. 397–409
  Berger, J., A. Neufeld, F. Becker, F. Lenzen und C. Schnörr
  
• (2015). „Shape from Texture using Locally Scaled Point Processes“. In: Image Anal. Stereol. 34.3, S. 161–170
  Didden, E.-M., T. Thorarinsdottir, A. Lenkoski und C. Schnörr
  
• (2015). „Solution-Driven Adaptive Total Variation Regularization“. In: Scale Space and Variational Methods. Springer International Publishing, S. 203–215
  Lenzen, F. und J. Berger
  
• (2015). „Spatiotemporal Parsing of Motor Kinematics for Assessing Stroke Recovery“. In: Medical Image Computing and Computer-Assisted Intervention - MICCAI
  Antic, B., U. Büchler, A. Wahl, M. E. Schwab und B. Ommer
  
• (2015). „Structures of Multivariate Dependence“. Diss. Faculty of Mathematics und Computer Science, Heidelberg University
  Edelmann, D.
  
• (2016). „A Geometric Approach to Image Labeling“. In: Proc. ECCV. Springer, S. 139–154
  Åström, F., S. Petra, B. Schmitzer und C. Schnörr
  
• (2016). „Automated Segmentation for Connectomics Utilizing higher-Order Biological Priors“. Diss. Faculty of Physics und Astronomy, Heidelberg University
  Krasowski, N.
  
• (2016). „Automated Segmentation for Connectomics Utilizing Higher-Order Biological Priors“. Doctoral Thesis. Ruprecht-Karls-Universität Heidelberg, Faculty of Mathematics und Computer Science
  Krasowski, N. E.
  
• (2016). „CliqueCNN: Deep Unsupervised Exemplar Learning“. In: Proceedings of the Conference on Advances in Neural Information Processing Systems (NIPS)
  Bautista, M., A. Sanakoyeu, E. Sutter und B. Ommer
  
• (2016). „Color Image Regularization via Channel Mixing and Half Quadratic Minimization“. In: Proc. ICIP. IEEE, S. 4007–4011
  Åström, F.
  
• (2016). „Data Adaptive Inference for Locally Stationary Processes“. Diss. Faculty of Mathematics und Computer Science, Heidelberg University
  Richter, S.
  
• (2016). „Distances, Gegenbauer Expansions, Curls, and Dimples: On Dependence Measures for Random Fields“. Diss. Faculty of Mathematics und Computer Science, Heidelberg University
  Fiedler, J.
  
• (2016). „Double-Opponent Vectorial Total Variation“. In: Proc. ECCV. Springer, S. 644–659. ISBN: 978-3-319-46475-6
  Åström, F. und C. Schnörr
  
• (2016). „Higher-order Segmentation via Multicuts“. In: Comp. Vision Image Understanding 143, S. 104–119
  Kappes, J., M. Speth, G. Reinelt und C. Schnörr
  
• (2016). „Joint Recursive Monocular Filtering of Camera Motion and Disparity Map“. In: 38th German Conference on Pattern Recognition. Springer
  Berger, J. und C. Schnörr
  
• (2016). „Parametric Dictionary-Based Velocimetry for Echo PIV“. In: Proc. GCPR
  Bodnariuc, E., S. Petra, C. Poelma und C. Schnörr
  
• (2016). „Plane Wave Acoustic Superposition for Fast Ultrasound Imaging“. In: Proc. IUS
  Bodnariuc, E., M. Schiffner, S. Petra und C. Schnörr
  
• (2016). „Second Order Minimum Energy Filtering“. Diss. Faculty of Mathematics und Computer Science, Heidelberg University
  Berger, J.
  
• (2016). „Source Localization of Reaction- Diffusion Models for Brain Tumors“. In: Proc. GCPR. Springer, S. 414–425
  Jaroudi, R., G. Baravdish, F. Åström und B. T. Johansson
  
• (2016). „The Assignment Manifold: A smooth model for image labeling“. In: Proc. CVPR. DIFF- CVML, S. 1–9
  Åström, F., S. Petra, B. Schmitzer und C. Schnörr
  
• (2017). „A Dual Ascent Framework for Lagrangean Decomposition of Combinatorial Problems“. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  Swoboda, P., J. Kuske und B. Savchynskyy
  
• (2017). „A Geometric Approach for Color Image Regularization“. In: J. Comp. Vision Image Understanding 165. S. 43–59
  Åström, F. und C. Schnörr
  
• (2017). „A Novel Convex Relaxation for Non-binary Discrete Tomography“. In: Scale Space and Variational Methods in Computer Vision. Springer, S. 235–246
  Kuske, J., P. Swoboda und S. Petra
  
• (2017). „An objective comparison of cell-tracking algorithms“. In: Nature methods 14.12, S. 1141
  Ulman, V., M. Maška, K. Magnusson, O. Ronneberger, C. Haubold, S. Wolf, N. Harder, P. Matula, P. Matula, D. Svoboda, M. Radojevic u. a.
  
• (2017). „Compressed Motion Sensing“. In: Scale Space and Variational Methods in Computer Vision: 6th International Conference, SSVM 2017, Kolding, Denmark, June 4-8, 2017. Springer International Publishing, S. 602–613. ISBN: 978-3-319-58771-4
  Dalitz, R., S. Petra und C. Schnörr
  
• (2017). „Deep Semantic Feature Matching“. In: Proc. CVPR
  Ufer, N. und B. Ommer
  
• (2017). „Distance correlation coefficients for Lancaster distributions“. In: Journal of Multivariate Analysis 154, S. 19–39
  Dueck, J., D. Edelmann und D. Richards
  
• (2017). „Geometric Image Labeling with Global Convex Labeling Constraints“. In: Proc. EMMCVPR. LNCS. Springer
  Zern, A., K. Rohr und C. Schnörr
  
• (2017). „Gradient Flows on a Riemannian Submanifold for Discrete Tomography“. In: Proc. GCPR
  Zisler, M., F. Savarino, S. Petra und C. Schnörr
  
• (2017). „Graphical Model Parameter Learning by Inverse Linear Programming“. In: Proc. SSVM. Springer, S. 323–334. ISBN: 978-3-319-58771-4
  Trajkovska, V., P. Swoboda, F. Åström und S. Petra
  
• (2017). „Graphical Model Parameter Learning by Inverse Linear Programming“. In: Scale Space and Variational Methods in Computer Vision: 6th International Conference, SSVM 2017, Kolding, Denmark, June 4-8, 2017, Proceedings. Hrsg. von F. Lauze, Y. Dong und A. B. Dahl. LNCS 10302. Springer, S. 323–334
  Trajkovska, V., P. Swoboda, F. Åström und S. Petra
  
• (2017). „Image Labeling by Assignment“. In: J. Math. Imag. Vision 58.2, S. 211–238
  Åström, F., S. Petra, B. Schmitzer und C. Schnörr
  
• (2017). „Image Reconstruction by Multilabel Propagation“. In: Proc. SSVM. Springer, S. 247–259. ISBN: 978-3-319-58771-4
  Zisler, M., F. Åström, S. Petra und C. Schnörr
  
• (2017). „Learned Watershed: End-To-End Learning of Seeded Segmentation“. In: The IEEE International Conference on Computer Vision (ICCV)
  Wolf, S., L. Schott, U. Kothe und F. Hamprecht
  
• (2017). „Learning Probabilistic Graphical Models for Image Segmentation“. Diss. Faculty of Mathematics und Computer Science, Heidelberg University
  Trajkovska, V.
  
• (2017). „Learning Probabilistic Graphical Models for Image Segmentation“. Doctoral Thesis. Ruprecht-Karls-Universität Heidelberg, Faculty of Mathematics und Computer Science
  Trajkovska, V.
  
• (2017). „Locally Adaptive Probabilistic Models for Global Segmentation of Pathological OCT Scans“. In: Medical Image Computing and Computer Assisted Intervention (MICCAI), S. 177–184
  Rathke, F., M. Desana und C. Schnörr
  
• (2017). „MAP Image Labeling Using Wasserstein Messages and Geometric Assignment“. In: Proc. SSVM. Bd. 10302. LCNS. Springer
  Aström, F., R. Hühnerbein, F. Savarino, J. Recknagel und C. SchnörrAström, F., R. Hühnerbein, F. Savarino, J. Recknagel und C. Schnörr
  
• (2017). „MAP Image Labeling Using Wasserstein Messages and Geometric Assignment“. In: Proc. SSVM. Bd. 10302. LCNS. Springer
  Åström, F., R. Hühnerbein, F. Savarino, J. Recknagel und C. Schnörr
  
• (2017). „Neuron Segmentation with High-Level Biological Priors“. In: IEEE Transactions on Medical Imaging 37.4, S. 829–839
  Krasowski, N., T. Beier, G. Knott, U. Koethe, F. Hamprecht und A. Kreshuk
  
• (2017). „Numerical Integration of Riemannian Gradient Flows for Image Labeling“. In: Proc. SSVM. Bd. 10302. LNCS. Springer
  Savarino, F., R. Hühnerbein, F. Aström, J. Recknagel und C. Schnörr
  
• (2017). „Representations of Partition Problems and the Method of Moments“. Diss. Faculty of Mathematics und Computer Science, Heidelberg University
  Silvestri, F.
  
• (2017). „Representations of Partition Problems and the Method of Moments“. Doctoral Thesis. Ruprecht-Karls-Universität Heidelberg, Faculty of Mathematics und Computer Science
  Silvestri, F.
  
• (2017). „Second-Order Recursive Filtering on the Rigid-Motion Lie Group SE(3) Based on Nonlinear Observations“. In: Journal of Mathematical Imaging and Vision 58.1, S. 102–129
  Berger, J., F. Lenzen, F. Becker, A. Neufeld und C. Schnörr
  
• (2017). „Segmentation of cell structures using Model-Based Set Covering with Iterative Reweighting“. In: 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), S. 392–396
  Markowsky, P., S. Reith, T. E. Zuber, R. König, K. Rohr und C. Schnörr
  
• (2017). „Self-supervised Learning of Pose Embeddings from Spatiotemporal Relations in Videos“. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV)
  Sümer, Ö., T. Dencker und B. Ommer
  
• (2017). „Sum-Product Graphical Models: a Graphical Model Perspective on Sum-Product Networks“. Doctoral Thesis. Ruprecht-Karls-Universität Heidelberg, Faculty of Mathematics und Computer Science
  Desana, M.
  
• (2017). „Tracking objects with higher order interactions via delayed column generation“. In: Artificial Intelligence and Statistics, S. 1132–1140
  Wang, S., S. Wolf, C. Fowlkes und J. Yarkony
  
• (2017). „Unsupervised Video Understanding by Reconciliation of Posture Similarities“. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV)
  Milbich, T., M. A. Bautista, E. Sutter und B. Ommer
  
• (2018). „A Spectral Approach to Peak Velocity Estimation of Pipe Flows from Noisy Image Sequences“. In: Analele Stiintifice ale Univesitatii Ovidius Constanta
  Bodnariuc, E.
  
• (2018). „A Variational U-Net for Conditional Appearance and Shape Generation“. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  Esser, P., E. Sutter und B. Ommer
  
• (2018). „Compressed Motion Sensing and dynamic Tomography“. Diss. Faculty of Mathematics und Computer Science, Heidelberg University
  Breckner, R.
  
• (2018). „Image Labeling Based on Graphical Models Using Wasserstein Messages and Geometric Assignment“. In: SIAM J. Imaging Science 11.2, S. 1317–1362
  Hühnerbein, R., F. Savarino, F. Aström und C. Schnörr
  
• (2018). „Multiscale Adaptive Correlation Method for Ultrasound Speckle Image Velocimetry“. In: IEEE IUS
  Bodnariuc, E. und C. Schnörr
  
• (2018). „On Plane Wave Ultrasound Particle Image Velocimetry“. Diss. Faculty of Mathematics und Computer Science, Heidelberg University
  Bodnariuc, E.
  
• (2018). „Segmentation of Cell Nuclei using Intensity-based Model Fitting and Sequential Convex Programming“. In: Proc. IEEE ISBI, S. 654–657
  Kostrykin, L., C. Schnörr und K. Rohr
  
• (2018). „Simultaneous inference for time-varying models“. In: technical report
  Karmakar, S., S. Richter und W. B. Wu
  
• (2018). „Sum-Product Graphical Models: a Graphical Model Perspective on Sum-Product Networks“. Diss. Faculty of Mathematics und Computer Science, Heidelberg University
  Desana, M.
  
• (2018). „The mutex watershed: efficient, parameter-free image partitioning“. In: Proceedings of the European Conference on Computer Vision (ECCV), S. 546–562
  Wolf, S., C. Pape, A. Bailoni, N. Rahaman, A. Kreshuk, U. Kothe und F. Hamprecht
  
• (2018). „Unsupervised Label Learning on Manifolds by Spatially Regularized Geometric Assignment“. In: GCPR. Springer, S. 698–713
  Zern, A., M. Zisler, F. Åström, S. Petra und C. Schnörr
  
• (2019). „A Variational Perspective on the Assignment Flow“. In: Proc. SSVM. Springer
  Savarino, F. und C. Schnörr
  
• (2019). „Cross validation for locally stationary processes“. In: The Annals of Statistics 47.4, S. 2145–2173
  Richter, S. und R. Dahlhaus
  
• (2019). „End-To-End Learned Random Walker for Seeded Image Segmentation“. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  Cerrone, L., A. Zeilmann und F. A. Hamprecht
  
• (2019). „Exponential Integration of the Linear Assignment Flow“. In: PAMM 19.1
  Zeilmann, A., F. Savarino, S. Petra und C. Schnörr
  
• (2019). „Fast Multivariate Log-Concave Density Estimation“. In: Comp. Statistics & Data Analysis 140, S. 41–58
  Rathke, F. und C. Schnörr
  
• (2019). „Globally Optimal Segmentation of Cell Nuclei in Fluorescence Microscopy Images using Shape and Intensity Information“. In: Medical Image Analysis 58, S. 101536
  Kostrykin, L., C. Schnörr und K. Rohr
  
• (2019). „Learning Adaptive Regularization for Image Labeling Using Geometric Assignment“. In: Proc. SSVM. Springer
  Hühnerbein, R., F. Savarino, S. Petra und C. Schnörr
  
• (2019). „LeMoNADe: Learned Motif and Neuronal Assembly Detection in calcium imaging videos“. In: International Conference on Learning Representations
  Kirschbaum, E., M. Haußmann, S. Wolf, H. Sonntag, J. Schneider, S. Elzoheiry, O. Kann, D. Durstewitz und F. Hamprecht
  
• (2019). „Performance Bounds For Co-/Sparse Box Constrained Signal Recovery“. In: Analele Universitatii Ovidius Constanta-Seria Matematica 27.1, S. 79–106
  Kuske, J. und S. Petra
  
• (2019). „Spatially Regularized Geometric Assignment for Unsupervised Label Learning on Manifolds“. In: PAMM 19.1.
  Zern, A., M. Zisler, S. Petra und C. Schnörr
  
• (2019). „Towards a general theory for non-linear locally stationary processes“. In: Bernoulli 25.2, S. 1013–1044
  Dahlhaus, R., S. Richter und W. B. Wu
  
• (2019). „Unsupervised Assignment Flow: Label Learning on Feature Manifolds by Spatially Regularized Geometric Assignment“. In: Journal of Mathematical Imaging and Vision
  Zern, A., M. Zisler, S. Petra und C. Schnörr
  
• (2019). „Unsupervised Labeling by Geometric and Spatially Regularized Self-Assignment“. In: Proc. SSVM. Springer
  Zisler, M., A. Zern, S. Petra und C. Schnörr
  
• (2020). „Geometric Numerical Integration of the Assignment Flow“. In: Inverse Problems
  Zeilmann, A., F. Savarino, S. Petra und C. Schnörr
  
• (2020). „Inference and Model Parameter Learning for Image Labeling by Geometric Assignment“. Diss. Faculty of Mathematics und Computer Science, Heidelberg University
  Hühnerbein, R.
  
• (2020). „Learning the Arrow of Time for Problems in Reinforcement Learning“. In: International Conference on Learning Representations
  Rahaman, N., S. Wolf, A. Goyal, R. Remme und Y. Bengio
  
• (2020). „Sum-Product Graphical Models“. In: Machine Learning 109, S. 135–173
  Desana, M. und C. Schnörr
  
• (2020). „The mutex watershed and its objective: Efficient, parameter-free image partitioning“. In: IEEE Transactions on Pattern Analysis & Machine Intelligence
  Wolf, S., A. Bailoni, C. Pape, N. Rahaman, A. Kreshuk, U. Kothe und F. Hamprecht
  
• (2020). „Variational Approaches for Image Labeling on the Assignment Manifold“. Diss. Faculty of Mathematics und Computer Science, Heidelberg University
  Savarino, F.