Deep learning-based algorithms have seen a massive popularity in different areas of remote
sensing image analysis over the past decade. Recently, transformer-based architectures …

The history of text can be traced back over thousands of years. Rich and precise semantic
information carried by text is important in a wide range of vision-based application …

Recently, transformer-based methods have achieved promising progresses in object
detection, as they can eliminate the post-processes like NMS and enrich the deep …

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 …

We introduce InternVL 2.5, an advanced multimodal large language model (MLLM) series
that builds upon InternVL 2.0, maintaining its core model architecture while introducing …

Over the past few years, the field of scene text detection has progressed rapidly that modern
text detectors are able to hunt text in various challenging scenarios. However, they might still …

State-of-the-art methods have achieved impressive performances on multi-oriented text
detection. Yet, they usually have difficulty in handling curved and dense texts, which are …

At present, text orientation is not diverse enough in the existing scene text datasets.
Specifically, curve-orientated text is largely out-numbered by horizontal and multi-oriented …

The flourishing blossom of deep learning has witnessed the rapid development of text
recognition in recent years. However, the existing text recognition methods are mainly …

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 …