Pattern Recognition

47th DAGM German Conference, DAGM GCPR 2025, Freiburg, Germany, September 23-26, 2025, Proceedings
Erscheinungsjahr 2026
ISBN: 978-3-032-12839-3
Verlag: Springer

Buch, Englisch, Band 16125, 649 Seiten, Format (B × H): 155 mm x 235 mm, Gewicht: 996 g

Reihe: Lecture Notes in Computer Science

This book constitutes the refereed proceedings of the 47th DAGM German Conference on Pattern Recognition, DAGM-GCPR 2025, held in Freiburg, Germany, during September 23-26, 2025.

The 40 full papers presented in this volume were carefully reviewed and selected from 85 submissions. 

They are grouped into the following topics: Computer Vision Systems and Applications; Video Analysis and Synthesis; Machine Learning Methods; Applications of Foundation Models; Safety and Robustness; 3D Perception and Reconstruction; Photogrammetry and Remote Sensing.

Zielgruppe

Research

Autoren/Hrsg.

Keuper, Margret

Locatello, Francesco

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Bildsignalverarbeitung
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz
• Mathematik | Informatik EDV | Informatik Angewandte Informatik
• Sozialwissenschaften Pädagogik Lehrerausbildung, Unterricht & Didaktik E-Learning, Bildungstechnologie

Inhaltsverzeichnis

.- Computer Vision Systems and Applications.

.-  Box it and Track it: A Weakly Supervised Framework for Cell Tracking.

.- A Cascaded Dilated Convolution Approach for Mpox Lesion Classification.

.- HistDiST: Histopathological Diffusion-based Stain Transfer.

.- Deep Learning-Assisted Dynamic Mode Decomposition for Non-resonant Background Removal in CARS Spectroscopy.

.- ?-Quant: Towards Learnable Quantization for Low-bit Pattern
 Recognition.

.- EVCS: A Benchmark for Fine-Grained Electric Vehicle Charging
 Station Detection.

.- Video Analysis and Synthesis.

.-  SegSLR: Promptable Video Segmentation for Isolated Sign Language
 Recognition.

.- Video Object Segmentation-aware Audio Generation.

.-  MCUCoder: Adaptive Bitrate Learned Video Compression for IoT Devices.

.- VisualChef: Generating Visual Aids in Cooking via Mask Inpainting.

.- StorySync: Training-Free Subject Consistency via Region Harmonization.

.-  Structured Universal Adversarial Attacks on Object Detection for
 Video Sequences.

.- Road Obstacle Video Segmentation.

.- Machine Learning Methods.

.- Don’t Miss Out on Novelty: Importance of Novel Features for Deep
 Anomaly Detection.

.- LADB: Latent Aligned Diffusion Bridges for Semi-Supervised Domain
 Translation.

.- On the Dangers of Bootstrapping Generation for Continual Learning
 and Beyond.

.-  Combined Image Data Augmentations diminish the benefits of
 Adaptive Label Smoothing.

.- Efficient Masked Attention Transformer for Few-Shot Classification
 and Segmentation.

.- Applications of Foundation Models.

.-  Using Knowledge Graphs to harvest datasets for efficient CLIP model
 training.

.- Unlocking In-Context Learning for Natural Datasets Beyond Language
 Modelling.

.-  Investigating Structural Pruning and Recovery Techniques for
 Compressing Multimodal Large Language Models: An Empirical Study.

.-  Assessing Foundation Models for Mold Colony Detection with Limited
 Training Data.

.- Common Data Properties Limit Object-Attribute Binding in CLIP.

.-  subCellSAM: Zero-Shot (Sub-)Cellular Segmentation for Hit Validation
 in Drug Discovery.

.- Safety and Robustness.

.-  synth-dacl: Does Synthetic Defect Data Enhance Segmentation
 Accuracy and Robustness for Real-World Bridge Inspections?.

.- FedPCE: Federated Personalized Client Embeddings for Post-training
 Knowledge Distillation.

.- Object Risk Estimation for Autonomous Driving Safety.

.- Rethinking Semi-supervised Segmentation Beyond Accuracy:
 Robustness and Reliability.

.-  Detection of Synthetic Face Images: Accuracy, Robustness, Generalization.

.- 3D Perception and Reconstruction.

.- MT-Occ: Single-View 3D Occupancy Prediction via Multi-Task Distillation.

.-  Hierarchical Insights: Exploiting Structural Similarities for Reliable 3D
 Semantic Segmentation.

.-  CoProU-VO: Combining Projected Uncertainty for End-to-End
 Unsupervised Monocular Visual Odometry.

.-  Combining Absolute and Semi-Generalized Relative Poses for Visual
 Localization.

.- Graph Roof Reconstruction with Synthetic Data from Misaligned Labels.

.-  sshELF: Single-Shot Hierarchical Extrapolation of Latent Features for
 3D Reconstruction from Sparse-Views.

.- Photogrammetry and Remote Sensing.

.- NaT-ReX: Naturalness Assessment with Transformer-Based Reliable
 Explainability.

.-  Semantic Segmentation of Structural Damage: A Comparative Study
 of YOLO11 and Encoder-Decoder Networks.

.- Can Multitask Learning Enhance Model Explainability?.

.-  Out-of-Distribution Detection in LiDAR Semantic Segmentation Using
 Epistemic Uncertainty from Hierarchical GMMs.

.- RadarSeq: A Temporal Vision Framework for User Churn Prediction
 via Radar Sequence Chart.