Bauckhage, ChristianGall, JürgenSchwing, Alexander2023-01-052023-01-052021978-3-030-92659-5978-3-030-92658-8https://publica.fraunhofer.de/handle/publica/41804110.1007/978-3-030-92659-5The proceedings contain 46 papers. The special focus in this conference is on Pattern Recognition. The topics include: Sublabel-Accurate Multilabeling Meets Product Label Spaces; investigating the Consistency of Uncertainty Sampling in Deep Active Learning; scaleNet: An Unsupervised Representation Learning Method for Limited Information; a New Split for Evaluating True Zero-Shot Action Recognition; video Instance Segmentation with Recurrent Graph Neural Networks; distractor-Aware Video Object Segmentation; (SP)2 Net for Generalized Zero-Label Semantic Segmentation; contrastive Representation Learning for Hand Shape Estimation; Fusion-GCN: Multimodal Action Recognition Using Graph Convolutional Networks; FIFA: Fast Inference Approximation for Action Segmentation; Hybrid SNN-ANN: Energy-Efficient Classification and Object Detection for Event-Based Vision; infoSeg: Unsupervised Semantic Image Segmentation with Mutual Information Maximization; a Comparative Study of PnP and Learning Approaches to Super-Resolution in a Real-World Setting; Merging-ISP: Multi-exposure High Dynamic Range Image Signal Processing; spatiotemporal Outdoor Lighting Aggregation on Image Sequences; AttrLostGAN: Attribute Controlled Image Synthesis from Reconfigurable Layout and Style; learning Conditional Invariance Through Cycle Consistency; CAGAN: Text-To-Image Generation with Combined Attention Generative Adversarial Networks; txT: Crossmodal End-to-End Learning with Transformers; diverse Image Captioning with Grounded Style; leveraging Group Annotations in Object Detection Using Graph-Based Pseudo-labeling; quantifying Uncertainty of Image Labelings Using Assignment Flows; sampling-Free Variational Inference for Neural Networks with Multiplicative Activation Noise; implicit and Explicit Attention for Zero-Shot Learning; self-supervised Learning for Object Detection in Autonomous Driving; Assignment Flows and Nonlocal PDEs on Graphs; viewpoint-Tolerant Semantic Segmentation for Aerial Logistics; t6D-Direct: Transformers for Multi-object 6D Pose Direct Regression; tetraPackNet: Four-Corner-Based Object Detection in Logistics Use-Cases; detecting Slag Formations with Deep Convolutional Neural Networks; virtual Temporal Samples for Recurrent Neural Networks: Applied to Semantic Segmentation in Agriculture; weakly Supervised Segmentation Pretraining for Plant Cover Prediction; How Reliable Are Out-of-Distribution Generalization Methods for Medical Image Segmentation?en3D modelingaction recognitioncomputer visiongenerative modelsimage codingimage processingimage qualityimage reconstructioninternetmachine learningneural networksobject recognitionoptimizationpattern recognitionself-supervised learningvideo segmentationconference proceeding