Learning to read by spelling: towards unsupervised text recognition

This work presents a method for visual text recognition without using any paired supervisory data. We formulate the text recognition task as one of aligning the conditional distribution of strings predicted from given text images, with lexically valid strings sampled from target corpora. This enable...

全面介紹

書目詳細資料
Main Authors: Gupta, A, Vedaldi, A, Zisserman, A
格式: Conference item
語言:English
出版: Association for Computing Machinery 2020

相似書籍