Optical Character Recognition2020en

classic

Dataset from Papers With Code

Metrics:accuracy, cer, wer, f1

Current State of the Art

REL-RWMD k-NN

Unknown

96.85

accuracy

Showing 2 breakthroughs from Apr 2019 to Dec 2019

Apr 2019

ApproxRepSet

From paper: Rep the Set: Neural Networks for Learning Set Representations

96.2

Dec 2019

REL-RWMD k-NNCurrent SOTA

From paper: Speeding up Word Mover's Distance and its variants via properties of distances between embeddings

96.8

+0.6%

Total Improvement

0.6%

Time Span

Breakthroughs

Current SOTA

96.8

accuracyPrimary

#	Model	Score	Paper / Code	Date
1	REL-RWMD k-NN	96.85	Speeding up Word Mover's Distance and its variants via properties of distances between embeddings Code	Dec 2019
2	ApproxRepSet	96.24	Rep the Set: Neural Networks for Learning Set Representations Code	Apr 2019

Dec 2019Models: REL-RWMD k-NN

Apr 2019Models: ApproxRepSet