Vision-language pretraining models have achieved great success in suppor...
Document images are a ubiquitous source of data where the text is organi...
One of the major challenges in training text-to-image generation models ...
Cross-Domain Detection (XDD) aims to train an object detector using labe...
This paper presents a GAN for generating images of handwritten lines
con...
Decomposing images of document pages into high-level semantic regions (e...
Automatic, template-free extraction of information from form images is
c...
Training state-of-the-art offline handwriting recognition (HWR) models
r...
When digitizing a document into an image, it is common to include a
surr...
Classifying pages or text lines into font categories aids transcription
...
Binarization of degraded historical manuscript images is an important
pr...
Convolutional Neural Networks (CNNs) are state-of-the-art models for doc...