Related papers: Automatic Training Data Synthesis for Handwriting …

Recently, there has been a surge in face personalization techniques, benefiting from the advanced capabilities of pretrained text-to-image diffusion models. Among these, a notable method is Textual Inversion, which generates personalized…

The generation of images of realistic looking, readable handwritten text is a challenging task which is referred to as handwritten text generation (HTG). Given a string and examples from a writer, the goal is to synthesize an image…

Stroke extraction of Chinese characters plays an important role in the field of character recognition and generation. The most existing character stroke extraction methods focus on image morphological features. These methods usually lead to…

We used Data Maps to model and characterize the AuTexTification dataset. This provides insights about the behaviour of individual samples during training across epochs (training dynamics). We characterized the samples across 3 dimensions:…

We introduce OmniPrint, a synthetic data generator of isolated printed characters, geared toward machine learning research. It draws inspiration from famous datasets such as MNIST, SVHN and Omniglot, but offers the capability of generating…

Self-supervised learning has emerged as a powerful approach for leveraging large-scale unlabeled data to improve model performance in various domains. In this paper, we explore masked self-supervised pre-training for text recognition…

Handwriting is a skill learned by humans from a very early age. The ability to develop one's own unique handwriting as well as mimic another person's handwriting is a task learned by the brain with practice. This paper deals with this very…

The recent progress in sparse coding and deep learning has made unsupervised feature learning methods a strong competitor to hand-crafted descriptors. In computer vision, success stories of learned features have been predominantly reported…

Modern deep learning models in computer vision require large datasets of real images, which are difficult to curate and pose privacy and legal concerns, limiting their commercial use. Recent works suggest synthetic data as an alternative,…

Hand-crafted mutants are increasingly used to evaluate fuzzing and property-based testing tools, but current tooling is fragmented and often forces trade-offs between readability, mutation preservation, and execution cost. We present a…

With recent advances in speech synthesis, synthetic data is becoming a viable alternative to real data for training speech recognition models. However, machine learning with synthetic data is not trivial due to the gap between the synthetic…

The essential task of verifying person identities at airports and national borders is very time consuming. To accelerate it, optical character recognition for identity documents (IDs) using dictionaries is not appropriate due to high…

Many analysis and prediction tasks require the extraction of structured data from unstructured texts. However, an annotation scheme and a training dataset have not been available for training machine learning models to mine structured data…

This paper demonstrates the systematic use of combinatorial coverage for selecting and characterizing test and training sets for machine learning models. The presented work adapts combinatorial interaction testing, which has been…

In text recognition, self-supervised pre-training emerges as a good solution to reduce dependence on expansive annotated real data. Previous studies primarily focus on local visual representation by leveraging mask image modeling or…

Recognizing handwriting images is challenging due to the vast variation in writing style across many people and distinct linguistic aspects of writing languages. In Vietnamese, besides the modern Latin characters, there are accent and…

Recent advancements in Deep Learning-based Handwritten Text Recognition (HTR) have led to models with remarkable performance on both modern and historical manuscripts in large benchmark datasets. Nonetheless, those models struggle to obtain…

Pathology foundation models learn morphological representations through self-supervised pretraining on large-scale whole-slide images, yet they do not explicitly capture the underlying molecular state of the tissue. Spatial transcriptomics…

Contour based scene text detection methods have rapidly developed recently, but still suffer from inaccurate frontend contour initialization, multi-stage error accumulation, or deficient local information aggregation. To tackle these…

This paper serves to introduce the Align, Minimize and Diversify (AMD) method, a Source-Free Unsupervised Domain Adaptation approach for Handwritten Text Recognition (HTR). This framework decouples the adaptation process from the source…