A major limitation to most state-of-the-art visual localization methods is their ineptitude to
make use of ubiquitous signs and directions that are typically intuitive to humans …

Accurate and efficient text detection in natural scenes is a fundamental yet challenging task
in computer vision, especially when dealing with arbitrarily-oriented texts. Most …

Recent text detection frameworks require several handcrafted components such as anchor
generation, non-maximum suppression (NMS), or multiple processing stages (eg label …

Text recognition methods are gaining rapid development. Some advanced techniques, eg,
powerful modules, language models, and un-and semi-supervised learning schemes …

Low illumination, under which discriminative clues are buried in the captured images, is an
under-investigated but noteworthy issue in wild scene text detection. Existing deep learning …

Positional Encoding (PE) plays a vital role in a Transformer's ability to capture the order of
sequential information, allowing it to overcome the permutation equivarience property …

Scene text detection frameworks heavily rely on optimization methods for their successful
operation. Choosing an appropriate optimizer is essential to performing recent scene text …

Motivated by the need to leverage technologies to enhance the preservation, accessibility,
quantitative data analysis, and valorization of Dance Heritage, this work introduces DanXe …

The performance of existing deep-learning scene text recognition-based methods fails
significantly on occluded text instances or even partially occluded characters in a text due to …

Scene text reading includes both scene text detection and recognition tasks. These tasks
face several challenges including text pattern variability, background complexity and scene …