Pattern Recognition: 41st DAGM German Conference, DAGM GCPR 2019, Dortmund, Germany, September 10–13, 2019, Proceedings (Lecture Notes in Computer Science Book 11824)

This book constitutes the proceedings of the 41st DAGM German Conference on Pattern Recognition, DAGM GCPR 2019, held in Dortmund, Germany, in September 2019. The 43 revised full papers presented were carefully reviewed and selected from 91 submissions. The German Conference on Pattern Recognition is the annual symposium of the German Association for Pattern Recognition (DAGM). It is the national venue for recent advances in image processing, pattern recognition, and computer vision and it follows the long tradition of the DAGM conference series. Front Matter ....Pages i-xvi Front Matter ....Pages 1-1 Learned Collaborative Stereo Refinement (Patrick Knöbelreiter, Thomas Pock)....Pages 3-17 Plane Completion and Filtering for Multi-View Stereo Reconstruction (Andreas Kuhn, Shan Lin, Oliver Erdler)....Pages 18-32 Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shift (Petra Bevandić, Ivan Krešo, Marin Oršić, Siniša Šegvić)....Pages 33-47 3D Bird’s-Eye-View Instance Segmentation (Cathrin Elich, Francis Engelmann, Theodora Kontogianni, Bastian Leibe)....Pages 48-61 Classification-Specific Parts for Improving Fine-Grained Visual Categorization (Dimitri Korsch, Paul Bodesheim, Joachim Denzler)....Pages 62-75 Front Matter ....Pages 77-77 Adjustment and Calibration of Dome Port Camera Systems for Underwater Vision (Mengkun She, Yifan Song, Jochen Mohrmann, Kevin Köser)....Pages 79-92 Training Auto-Encoder-Based Optimizers for Terahertz Image Reconstruction (Tak Ming Wong, Matthias Kahl, Peter Haring-Bolívar, Andreas Kolb, Michael Möller)....Pages 93-106 Joint Viewpoint and Keypoint Estimation with Real and Synthetic Data (Pau Panareda Busto, Juergen Gall)....Pages 107-121 Non-causal Tracking by Deblatting (Denys Rozumnyi, Jan Kotera, Filip Šroubek, Jiří Matas)....Pages 122-135 Front Matter ....Pages 137-137 Group Pruning Using a Bounded-\(\ell _p\) Norm for Group Gating and Regularization (Chaithanya Kumar Mummadi, Tim Genewein, Dan Zhang, Thomas Brox, Volker Fischer)....Pages 139-155 On the Estimation of the Wasserstein Distance in Generative Models (Thomas Pinetz, Daniel Soukup, Thomas Pock)....Pages 156-170 Deep Archetypal Analysis (Sebastian Mathias Keller, Maxim Samarin, Mario Wieser, Volker Roth)....Pages 171-185 Front Matter ....Pages 187-187 Single Level Feature-to-Feature Forecasting with Deformable Convolutions (Josip Šarić, Marin Oršić, Tonći Antunović, Sacha Vražić, Siniša Šegvić)....Pages 189-202 Predicting Landscapes from Environmental Conditions Using Generative Networks (Christian Requena-Mesa, Markus Reichstein, Miguel Mahecha, Basil Kraft, Joachim Denzler)....Pages 203-217 Semi-supervised Segmentation of Salt Bodies in Seismic Images Using an Ensemble of Convolutional Neural Networks (Yauhen Babakhin, Artsiom Sanakoyeu, Hirotoshi Kitamura)....Pages 218-231 Entrack: A Data-Driven Maximum-Entropy Approach to Fiber Tractography (Viktor Wegmayr, Giacomo Giuliari, Joachim M. Buhmann)....Pages 232-244 Front Matter ....Pages 245-245 Generative Aging of Brain MR-Images and Prediction of Alzheimer Progression (Viktor Wegmayr, Maurice Hörold, Joachim M. Buhmann)....Pages 247-260 Nonlinear Causal Link Estimation Under Hidden Confounding with an Application to Time Series Anomaly Detection (Violeta Teodora Trifunov, Maha Shadaydeh, Jakob Runge, Veronika Eyring, Markus Reichstein, Joachim Denzler)....Pages 261-273 Iris Verification with Convolutional Neural Network and Unit-Circle Layer (Radim Špetlík, Ivan Razumenić)....Pages 274-287 SDNet: Semantically Guided Depth Estimation Network (Matthias Ochs, Adrian Kretz, Rudolf Mester)....Pages 288-302 Object Segmentation Using Pixel-Wise Adversarial Loss (Ricard Durall, Franz-Josef Pfreundt, Ullrich Köthe, Janis Keuper)....Pages 303-316 Visual Coin-Tracking: Tracking of Planar Double-Sided Objects (Jonáš Šerých, Jiří Matas)....Pages 317-330 Exploiting Attention for Visual Relationship Detection (Tongxin Hu, Wentong Liao, Michael Ying Yang, Bodo Rosenhahn)....Pages 331-344 Learning Task-Specific Generalized Convolutions in the Permutohedral Lattice (Anne S. Wannenwetsch, Martin Kiefel, Peter V. Gehler, Stefan Roth)....Pages 345-359 Achieving Generalizable Robustness of Deep Neural Networks by Stability Training (Jan Laermann, Wojciech Samek, Nils Strodthoff)....Pages 360-373 2D and 3D Segmentation of Uncertain Local Collagen Fiber Orientations in SHG Microscopy (Lars Schmarje, Claudius Zelenka, Ulf Geisen, Claus-C. Glüer, Reinhard Koch)....Pages 374-386 Points2Pix: 3D Point-Cloud to Image Translation Using Conditional GANs (Stefan Milz, Martin Simon, Kai Fischer, Maximillian Pöpperl, Horst-Michael Gross)....Pages 387-400 MLAttack: Fooling Semantic Segmentation Networks by Multi-layer Attacks (Puneet Gupta, Esa Rahtu)....Pages 401-413 Not Just a Matter of Semantics: The Relationship Between Visual and Semantic Similarity (Clemens-Alexander Brust, Joachim Denzler)....Pages 414-427 DynGraph: Visual Question Answering via Dynamic Scene Graphs (Monica Haurilet, Ziad Al-Halah, Rainer Stiefelhagen)....Pages 428-441 Training Invertible Neural Networks as Autoencoders (The-Gia Leo Nguyen, Lynton Ardizzone, Ullrich Köthe)....Pages 442-455 Weakly Supervised Learning of Dense Semantic Correspondences and Segmentation (Nikolai Ufer, Kam To Lui, Katja Schwarz, Paul Warkentin, Björn Ommer)....Pages 456-470 A Neural-Symbolic Architecture for Inverse Graphics Improved by Lifelong Meta-learning (Michael Kissner, Helmut Mayer)....Pages 471-484 Unsupervised Multi-source Domain Adaptation Driven by Deep Adversarial Ensemble Learning (Sayan Rakshit, Biplab Banerjee, Gemma Roig, Subhasis Chaudhuri)....Pages 485-498 Time-Frequency Causal Inference Uncovers Anomalous Events in Environmental Systems (Maha Shadaydeh, Joachim Denzler, Yanira Guanche García, Miguel Mahecha)....Pages 499-512 Tongue Contour Tracking in Ultrasound Images with Spatiotemporal LSTM Networks (Enes Aslan, Yusuf Sinan Akgul)....Pages 513-521 Localized Interactive Instance Segmentation (Soumajit Majumder, Angela Yao)....Pages 522-536 Iterative Greedy Matching for 3D Human Pose Tracking from Multiple Views (Julian Tanke, Juergen Gall)....Pages 537-550 Visual Person Understanding Through Multi-task and Multi-dataset Learning (Kilian Pfeiffer, Alexander Hermans, István Sárándi, Mark Weber, Bastian Leibe)....Pages 551-566 Dynamic Classifier Chains for Multi-label Learning (Pawel Trajdos, Marek Kurzynski)....Pages 567-580 Learning 3D Semantic Reconstruction on Octrees (Xiaojuan Wang, Martin R. Oswald, Ian Cherabier, Marc Pollefeys)....Pages 581-594 Learning to Disentangle Latent Physical Factors for Video Prediction (Deyao Zhu, Marco Munderloh, Bodo Rosenhahn, Jörg Stückler)....Pages 595-608 Learning to Train with Synthetic Humans (David T. Hoffmann, Dimitrios Tzionas, Michael J. Black, Siyu Tang)....Pages 609-623 Back Matter ....Pages 625-626