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...
| Main Authors: | , , |
|---|---|
| Formato: | Conference item |
| Idioma: | English |
| Publicado em: |
Association for Computing Machinery
2020
|