TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Model

arXiv:2403.10047v1 Announce Type: new
Abstract: Existing scene text spotters are designed to locate and transcribe texts from images. However, it is challenging for a spotter to achieve precise detection and recognition of scene texts simultaneously. Inspired by the glimpse-focus spotting pipeline of human beings and impressive performances of Pre-trained Language Models (PLMs) on visual tasks, we ask: 1) "Can machines spot texts without precise detection just like human beings?", and if yes, 2) "Is text block another alternative for scene …

abstract arxiv beings cs.cv detection focus free however human images language language model performances pipeline recognition text transcribe type