Conference item icon

Conference item

Learning to read by spelling: towards unsupervised text recognition

Abstract:

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 enables fully automated, and unsupervised learning from just line-level text-images, and unpaired text-string samples, obviating the need for large aligned datasets. We present detailed analysis for vari...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1145/3293353.3293386

Authors


More by this author
Institution:
University of Oxford
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Oxford college:
New College
Role:
Author
More by this author
Institution:
University of Oxford
Department:
Engineering Science
Role:
Author
More from this funder
Name:
Engineering and Physical Sciences Research Council
Grant:
EP/M013774/1
Publisher:
Association for Computing Machinery
Host title:
ICVGIP 2018: Proceedings of the 11th Indian Conference on Computer Vision, Graphics and Image Processing
Article number:
33
Publication date:
2020-05-03
Acceptance date:
2018-11-10
Event title:
11th Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP 2018)
Event location:
Hyderabad, India
Event website:
https://cvit.iiit.ac.in/icvgip18
Event start date:
2018-12-18
Event end date:
2018-12-22
DOI:
ISBN:
9781450366151
Language:
English
Keywords:
Pubs id:
pubs:956236
UUID:
uuid:1a12a6cb-291d-433b-a004-5b289c8cb9cd
Local pid:
pubs:956236
Source identifiers:
956236
Deposit date:
2019-01-04

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP