Pattern Recognition: 40th German Conference, GCPR 2018, Stuttgart, Germany, October 9-12, 2018, Proceedings(Image Processing, Computer Vision, Pattern Recognition, and Graphics)

About the Book

This book constitutes the refereed proceedings of the 40th German Conference on Pattern Recognition, GCPR 2018, held in Stuttgart, Germany, in October 2018.

The 48 revised full papers presented were carefully reviewed and selected from 118 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, which has been renamed to GCPR in 2013 to reflect its increasing internationalization. In 2018 in Stuttgart, the conference series celebrated its 40th anniversary.

Table of Contents:
Topology-Based 3D Reconstruction of Mid-level Primitives in Man-Made Environments.- Associative Deep Clustering: Training a Classification Network with No Labels.- A Table Tennis Robot System Using An Industrial KUKA Robot Arm.- View-Aware Person Re-Identification.- MC2SLAM: Real-Time Inertial Lidar Odometry Using Two-Scan Motion Compensation.- An Analysis by Synthesis Approach for Automatic Vertebral Shape Identification in Clinical QCT.- Parcel Tracking in Large Camera Networks.- Segmentation of Head and Neck Organs at Risk Using CNN with Batch Dice Loss.- Detection of Mechanical Damages in Sawn Timber Using Convolutional Neural Networks.- Compressed-Domain Video Object Tracking Using Markov Random Fields with Graph Cuts Optimization.- Metric-Driven Learning of Correspondence Weighting for 2-D/3-D Image Registration.- Multi-view X-ray R-CNN.- Ex Paucis Plura: Learning Accordance Segmentation from Very Few Examples.- Domain Generalization with Domain-Specific Aggregation Modules.- X-GAN: Improving Generative Adversarial Networks with ConveX Combinations.- A Randomized Gradient-free Attack to ReLU Networks .- Cross and Learn: Cross-Modal Self-Supervision .- KS(conf): A Light-Weight Test if A ConvNet Operates Outside of Its Specifications.- Sublabel-accurate Convex Relaxation with Total Generalized Variation Regularization.- On the Integration of Optical Flow and Action Recognition.- Context-driven Multi-stream LSTM (M-LSTM) for Recognizing Fine-Grained Activity of Drivers.- 3D Fluid Flow Estimation with Integrated Particle Reconstruction.- NRST: Non-rigid Surface Tracking from Monocular Video.- Counting the Uncountable: Deep Semantic Density Estimation from Space .- Acquire, Augment, Segment and Enjoy: Weakly Supervised Instance Segmentation of Supermarket Products.- Vehicle Re-Identification in Context.- Low-Shot Learning of Plankton Categories.- Multimodal Dense Stereo Matching.- Deep Distance Transform to Segment Visually Indistinguishable Merged Objects.- Multi-class Cell Segmentation Using CNNs with F1-measure Loss Function.- Improved Semantic Stixels Via Multimodal Sensor Fusion.- Convolve, Attend and Spell: An Attention-based Sequence-to-Sequence Model for Handwritten Word Recognition.- Illumination Estimation Is Sufficient for Indoor-Outdoor Image Classification.- DeepKey: Towards End-to-End Physical Key Replication from a Single Photograph.- Deriving Neural Network Architectures Using Precision Learning: Parallel-to-fan Beam Conversion.- Detecting Face Morphing Attacks by Analyzing the Directed Distances of Facial Landmarks Shifts.- KloudNet: Deep Learning for Sky Image Analysis and Irradiance Forecasting.- Learning Style Compatibility for Furniture.- Temporal Interpolation as An Unsupervised Pretraining Task for Optical Flow Estimation.- Decoupling Respiratory and Angular Variation in Rotational X-ray Scans Using a Prior Bilinear Model.- Inference, Learning and Attention Mechanisms that Exploit and Preserve Sparsity in CNNs.- End-to-endLearning of Deterministic Decision Trees.- Taming the Cross Entropy Loss.- Supervised Deep Kriging for Single-Image Super-Resolution.- Information-Theoretic Active Learning for Content-Based Image Retrieval.- AFSI: Adaptive Restart for Fast Semi-Iterative Schemes for Convex Optimization.- Invexity Preserving Transformations for Projection Free Optimization with Sparsity Inducing Non-Convex Constraints.- Unsupervised Label Learning on Manifolds by Spatially Regularized Geometric Assignment.