works on

From the 1 of 5 linked papers with an AI index.

most citedZero-Shot Paragraph-level Handwriting Imitation with Latent Diffusion Models

1 citations · 1 across the 4 of their papers we have counts for

collaborators
Showing cs.CVShow all

5 papers · 1 filter

cs.CV20261 cited

Zero-Shot Paragraph-level Handwriting Imitation with Latent Diffusion Models

Martin Mayr, Marcel Dreier, Florian Kordon +6

The paper presents a zero-shot method for generating entire paragraphs of handwritten text in unseen styles using a modified latent diffusion model that jointly conditions on a sty…

cs.CV2026

Handwriting Extraction and Analysis of Signature Lists in Swiss Popular Initiatives

Marco Peer, Thomas Gorges, Mathias Seuret +2

Popular initiatives and referendums are central to Swiss democracy, yet the validation of handwritten signature lists remains a labor-intensive manual process. This paper investiga…

cs.CV2026

ICDAR 2026 Competition on Writer Identification and Pen Classification from Hand-Drawn Circles

Thomas Gorges, Janne van der Loop, Lukas Hüttner +4

This paper presents CircleID, a large-scale ICDAR 2026 competition on writer identification and pen classification from scanned hand-drawn circles. The primary objective is to inve…

cs.CV2026

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…

cs.CV2024

Deep Generalized Max Pooling

Vincent Christlein, Lukas Spranger, Mathias Seuret +3

Global pooling layers are an essential part of Convolutional Neural Networks (CNN). They are used to aggregate activations of spatial locations to produce a fixed-size vector in se…