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...
Үндсэн зохиолчид: | Gupta, A, Vedaldi, A, Zisserman, A |
---|---|
Формат: | Conference item |
Хэл сонгох: | English |
Хэвлэсэн: |
Association for Computing Machinery
2020
|
Ижил төстэй зүйлс
-
Learning to read by spelling: towards unsupervised text recognition
-н: Gupta, A, зэрэг
Хэвлэсэн: (2018) -
Deep structured output learning for unconstrained text recognition
-н: Jaderberg, M, зэрэг
Хэвлэсэн: (2015) -
Deep structured output learning for unconstrained text recognition
-н: Jaderberg, M, зэрэг
Хэвлэсэн: (2014) -
Object class recognition by unsupervised scale-invariant learning
-н: Fergus, R, зэрэг
Хэвлэсэн: (2003) -
Phonology and morphology in learning to read and to spell
-н: Bryant, P, зэрэг
Хэвлэсэн: (2000)