Mathias Zinnen

Mathias Zinnen, M. Sc.

Researcher

Department of Computer Science
Chair of Computer Science 5 (Pattern Recognition)

Room: Room 9.156
Martensstr. 3
91058 Erlangen

Academic CV

Mathias Zinnen studied philosophy and computer science in Berlin and Erlangen. Currently pursuing a Ph.D. in FAU Erlangen’s Pattern Recognition Lab, his research centers on computer vision in arts. His main academic interests cover object detection, pose estimation, and multimodal methods, along with innovative work on visual representations of smell.

Projects

No projects found.

Publications

2025

Journal Articles

Conference Contributions

2024

Journal Articles

Conference Contributions

2023

Journal Articles

Conference Contributions

2022

Conference Contributions

2021

Conference Contributions

Lectures

No matching records found.

Theses

Type Title Status
MA thesis From Pixels to Structure: Analysis of Lightweight Vision-Language Models for Document OCR and Structured Output Generation running
MA thesis Investigation on Object Detection in Industrial Settings Centered on Extended Reality Platforms Through Generation and Utilization of Synthetic Data from CAD Models running
MA thesis Unsupervised Image Retrieval for Auction Catalogues running
BA thesis Context-Aware Emotion Recognition from Pictures using Frozen CLIP running
MA thesis Multimodal fusion of pose and visual information for gesture recognition in historical artworks running
Project Unsupervised detection running
MA thesis Pre-processing and synthetic data generation techniques for defect detection in SiC and AlN wafers running
MA thesis CADGLM – Integrating Graph Neural Networks and Large Language Models to Predict Machining Information from Graph Representations of 3D Models finished
MA thesis Enhancing small-sized video object detection through temporal information and synthetic data finished
MA thesis Data Augmentation for Artwork Object Detection via Latent Diffusion Models finished
MA thesis Real-Time Traffic Sign Detection for Smart Data Logging finished
MA thesis Improving OCR for Structured Documents using Domain Knowledge finished
MA thesis Multimodal Gesture Classification in Artwork Images finished
MA thesis Investigating the benefits of combining CNNs and transformer architecture for rail domain perception task finished
MA thesis Exploring Stylistic Invariance in Self-Supervised Pretraining for Feature Extraction finished
MA thesis ML based Classification of States in LPWAN Current Consumption Curves finished
MA thesis Object Consistency GAN for Object Detection Pretraining finished
MA thesis Improving Instance Localization for Object Detection Pretraining finished
MA thesis Multi-task Learning for Molecular Odor Prediction With Multiple Datasets finished