15 citations · 51 across the 12 of their papers we have counts for
12 papers
AI Application Benchmarking: Power-Aware Performance Analysis for Vision and Language Models
Martin Mayr, Sebastian Wind, Lukas Schröder +4
Artificial Intelligence (AI) workloads drive a rapid expansion of high-performance computing (HPC) infrastructures and increase their power and energy demands towards a critical le…
DRetHTR: Linear-Time Decoder-Only Retentive Network for Handwritten Text Recognition
Changhun Kim, Martin Mayr, Thomas Gorges +4
State-of-the-art handwritten text recognition (HTR) systems commonly use Transformers, whose growing key-value (KV) cache makes decoding slow and memory-intensive. We introduce DRe…
SteuerLLM: Local specialized large language model for German tax law analysis
Sebastian Wind, Jeta Sopa, Laurin Schmid +8
Large language models (LLMs) demonstrate strong general reasoning and language understanding, yet their performance degrades in domains governed by strict formal rules, precise ter…
SSL4SAR: Self-Supervised Learning for Glacier Calving Front Extraction from SAR Imagery
Nora Gourmelon, Marcel Dreier, Martin Mayr +5
Glaciers are losing ice mass at unprecedented rates, increasing the need for accurate, year-round monitoring to understand frontal ablation, particularly the factors driving the ca…
Nuremberg Letterbooks: A Multi-Transcriptional Dataset of Early 15th Century Manuscripts for Document Analysis
Martin Mayr, Julian Krenz, Katharina Neumeier +8
Most datasets in the field of document analysis utilize highly standardized labels, which, while simplifying specific tasks, often produce outputs that are not directly applicable…
Zero-Shot Paragraph-level Handwriting Imitation with Latent Diffusion Models
Martin Mayr, Marcel Dreier, Florian Kordon +5
The imitation of cursive handwriting is mainly limited to generating handwritten words or lines. Multiple synthetic outputs must be stitched together to create paragraphs or whole…
A Fair Evaluation of Various Deep Learning-Based Document Image Binarization Approaches
Richin Sukesh, Mathias Seuret, Anguelos Nicolaou +2
Binarization of document images is an important pre-processing step in the field of document analysis. Traditional image binarization techniques usually rely on histograms or local…
Combining OCR Models for Reading Early Modern Printed Books
Mathias Seuret, Janne van der Loop, Nikolaus Weichselbaumer +6
In this paper, we investigate the usage of fine-grained font recognition on OCR for books printed from the 15th to the 18th century. We used a newly created dataset for OCR of earl…
Writer Retrieval and Writer Identification in Greek Papyri
Vincent Christlein, Isabelle Marthot-Santaniello, Martin Mayr +2
The analysis of digitized historical manuscripts is typically addressed by paleographic experts. Writer identification refers to the classification of known writers while writer re…
SmartPatch: Improving Handwritten Word Imitation with Patch Discriminators
Alexander Mattick, Martin Mayr, Mathias Seuret +2
As of recent generative adversarial networks have allowed for big leaps in the realism of generated images in diverse domains, not the least of which being handwritten text generat…
Spatio-Temporal Handwriting Imitation
Martin Mayr, Martin Stumpf, Anguelos Nicolaou +3
Most people think that their handwriting is unique and cannot be imitated by machines, especially not using completely new content. Current cursive handwriting synthesis is visuall…
Weakly Supervised Segmentation of Cracks on Solar Cells using Normalized Lp Norm
Martin Mayr, Mathis Hoffmann, Andreas Maier +1
Photovoltaic is one of the most important renewable energy sources for dealing with world-wide steadily increasing energy consumption. This raises the demand for fast and scalable…