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...

Бүрэн тодорхойлолт

Номзүйн дэлгэрэнгүй
Үндсэн зохиолчид: Gupta, A, Vedaldi, A, Zisserman, A
Формат: Conference item
Хэл сонгох:English
Хэвлэсэн: Association for Computing Machinery 2020

Ижил төстэй зүйлс