Optical character recognition (OCR) is the process of extracting handwritten or printed text
from a scanned or printed image and converting it to a machine-readable form for further …

Visual representation learning is ubiquitous in various real-world applications, including
visual comprehension, video understanding, multi-modal analysis, human-computer …

Context-aware STR methods typically use internal autoregressive (AR) language models
(LM). Inherent limitations of AR models motivated two-stage methods which employ an …

End-to-end text spotting aims to integrate scene text detection and recognition into a unified
framework. Dealing with the relationship between the two sub-tasks plays a pivotal role in …

Scene text recognition (STR) enables computers to read text in natural scenes such as
object labels, road signs and instructions. STR helps machines perform informed decisions …

Scene text recognition (STR) has been an active research topic in computer vision for years.
To tackle this challenging problem, numerous innovative methods have been successively …

We propose a framework for sequence-to-sequence contrastive learning (SeqCLR) of visual
representations, which we apply to text recognition. To account for the sequence-to …

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 …

Text spotting end-to-end methods have recently gained attention in the literature due to the
benefits of jointly optimizing the text detection and recognition components. Existing …

Pre-trained vision-language models (VLMs) are the de-facto foundation models for various
downstream tasks. However, scene text recognition methods still prefer backbones pre …