The Optical Character Recognition (OCR) systems have been widely used in various of
application scenarios, such as office automation (OA) systems, factory automations, online …

Current text recognition systems, including those for handwritten scripts and scene text, have
relied heavily on image synthesis and augmentation, since it is difficult to realize real-world …

Although text recognition has significantly evolved over the years, state-of the-art (SOTA)
models still struggle in the wild scenarios due to complex backgrounds, varying fonts …

Nowadays, scene text recognition has attracted more and more attention due to its various
applications. Most state-of-the-art methods adopt an encoder-decoder framework with …

The transformer-based encoder-decoder framework is becoming popular in scene text
recognition, largely because it naturally integrates recognition clues from both visual and …

Abstract We introduce Perceiving Stroke-Semantic Context (PerSec), a new approach to self-
supervised representation learning tailored for Scene Text Recognition (STR) task …

Self-supervised learning has gained prominence due to its efficacy at learning powerful
representations from unlabelled data that achieve excellent performance on many …

Handwriting, as a uniquely human skill, contributes to fine motor development and cognitive
growth. Beyond mere functionality, handwriting carries individuality and subtle emotional …

Recently self-supervised representation learning has drawn considerable attention from the
scene text recognition community. Different from previous studies using contrastive learning …

Data augmentation is an efficient way to expand a training dataset by creating additional
artificial data. While data augmentation is found to be effective in improving the …