|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM355233444 |
| 003 |
DE-627 |
| 005 |
20231226063922.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2023 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2023.3235826
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1184.xml
|
| 035 |
|
|
|a (DE-627)NLM355233444
|
| 035 |
|
|
|a (NLM)37018638
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Coquenet, Denis
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a DAN
|b A Segmentation-Free Document Attention Network for Handwritten Document Recognition
|
| 264 |
|
1 |
|c 2023
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Completed 06.06.2023
|
| 500 |
|
|
|a Date Revised 06.06.2023
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Unconstrained handwritten text recognition is a challenging computer vision task. It is traditionally handled by a two-step approach, combining line segmentation followed by text line recognition. For the first time, we propose an end-to-end segmentation-free architecture for the task of handwritten document recognition: the Document Attention Network. In addition to text recognition, the model is trained to label text parts using begin and end tags in an XML-like fashion. This model is made up of an FCN encoder for feature extraction and a stack of transformer decoder layers for a recurrent token-by-token prediction process. It takes whole text documents as input and sequentially outputs characters, as well as logical layout tokens. Contrary to the existing segmentation-based approaches, the model is trained without using any segmentation label. We achieve competitive results on the READ 2016 dataset at page level, as well as double-page level with a CER of 3.43% and 3.70%, respectively. We also provide results for the RIMES 2009 dataset at page level, reaching 4.54% of CER. We provide all source code and pre-trained model weights at https://github.com/FactoDeepLearning/DAN
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Chatelain, Clement
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Paquet, Thierry
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 45(2023), 7 vom: 10. Juli, Seite 8227-8243
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:45
|g year:2023
|g number:7
|g day:10
|g month:07
|g pages:8227-8243
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2023.3235826
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 45
|j 2023
|e 7
|b 10
|c 07
|h 8227-8243
|