Published October 24, 2022
| Version v1
Other
Open
Pretrained Vertical Attention Network for Handwritten Text Recognition
Creators
Description
Pre-trained weights of the Vertical Attention Network at line (pre-training stage) and paragraph levels on three datasets: IAM, READ 2016 and RIMES 2011.
Denis Coquenet, Clément Chatelain, Thierry Paquet, "End-to-end Handwritten Paragraph Text Recognition Using a Vertical Attention Network", IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022.
Source code: Github
Paper: Arxiv
Files
Files
(181.7 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:23f9bb8a68dba8020f3bdfb1892bdbfc
|
20.8 MB | Download |
|
md5:6ff96a2eee4484aba61d192fe397e4dc
|
32.7 MB | Download |
|
md5:daab13692efcd2fdcbdc65e991f46c95
|
20.8 MB | Download |
|
md5:b7e4b91e419a6ec5843ce992ea850323
|
32.8 MB | Download |
|
md5:c16410772222f362e5321db44318f373
|
20.9 MB | Download |
|
md5:48875a0d2b00328f4b0b334037833ee0
|
32.8 MB | Download |
|
md5:c902d5ef7ab25350146044d96ce6c3f9
|
20.8 MB | Download |
Additional details
References
- 10.1109/TPAMI.2022.3144899
- https://github.com/FactoDeepLearning/VerticalAttentionOCR