Large Vision-Language Models (LVLMs) have recently played a dominant role in
multimodal vision-language learning. Despite the great success, it lacks a holistic evaluation …

Neural compression is the application of neural networks and other machine learning
methods to data compression. Recent advances in statistical machine learning have opened …

Large models have recently played a dominant role in natural language processing and
multimodal vision-language learning. However, their effectiveness in text-related visual …

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 NVLM 1.0, a family of frontier-class multimodal large language models (LLMs)
that achieve state-of-the-art results on vision-language tasks, rivaling the leading proprietary …

This paper presents a comprehensive evaluation of the Optical Character Recognition
(OCR) capabilities of the recently released GPT-4V (ision), a Large Multimodal Model …

Existing handwritten text generation methods often require more than ten handwriting
samples as style references. However, in practical applications, users tend to prefer a …

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

Scene text images contain not only style information (font background) but also content
information (character texture). Different scene text tasks need different information but …

This paper aims at the distorted document image rectification problem, the objective to
eliminate the geometric distortion in the document images and realize document …