We present DeepSeek-VL, an open-source Vision-Language (VL) Model designed for real-
world vision and language understanding applications. Our approach is structured around …

Linguistic knowledge is of great benefit to scene text recognition. However, how to effectively
model linguistic rules in end-to-end deep networks remains a research challenge. In this …

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

This paper aims to re-assess scene text recognition (STR) from a data-oriented perspective.
We begin by revisiting the six commonly used benchmarks in STR and observe a trend of …

Typical text recognition methods rely on an encoder-decoder structure, in which the encoder
extracts features from an image, and the decoder produces recognized text from these …

Powered by remarkable advancements in Large Language Models (LLMs), Multimodal
Large Language Models (MLLMs) demonstrate impressive capabilities in manifold tasks …

Scene text spotting is of great importance to the computer vision community due to its wide
variety of applications. Recent methods attempt to introduce linguistic knowledge for …

Scene text recognition (STR) task has a common practice: All state-of-the-art STR models
are trained on large synthetic data. In contrast to this practice, training STR models only on …

The diversity in length constitutes a significant characteristic of text. Due to the long-tail
distribution of text lengths, most existing methods for scene text recognition (STR) only work …

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 …