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

In text recognition, self-supervised pre-training emerges as a good solution to reduce
dependence on expansive annotated real data. Previous studies primarily focus on local …

The main objective of scene text recognition is to recognize text in complex images and
convert it into editable text. However, scene text recognition research has long been focused …

开放集文字识别(Open-set text recognition, OSTR) 是一项新任务, 旨在解决开放环境下文字
识别应用中的语言模型偏差及新字符识别与拒识问题. 最近的OSTR 方法通过将上下文信息与 …

In this paper, we investigate cross-lingual learning (CLL) for multilingual scene text
recognition (STR). CLL transfers knowledge from one language to another. We aim to find …

The foremost challenge in continual learning is devising strategies to alleviate catastrophic
forgetting, thereby preserving a model's memory of prior knowledge while learning new …