List your company

Scene Text Recognition on SVT Perspective

94.3AccuracyLiu et al.
21.91640.70859.578.292Jan 10, 2019Jul 21, 2019Jan 29, 2020Aug 8, 2020Feb 16, 2021Aug 27, 2021Mar 7, 2022

Evaluation results

MethodLinks
Liu et al.Lexicon=502019.0194.3
MORANLexicon=502019.0194.3
Cheng et al. [6]Lexicon=502019.0194
Yang et al.Lexicon=502019.0193
Cheng et al. [5]Lexicon=502019.0192.6
Shi et al.Lexicon=502019.0191.2
SIGATType=V, Backbone=ViT-B, Structure=Transformer, Size=32×1282022.0390.5
ABINetType=VL, Backbone=ResNet45-Trns, Structure=Transformer, Size=32×1282022.0389.3
ABINet+ConCLRType=VL, Backbone=ResNet45-Trns, Structure=Transformer, Size=32×1282022.0389.3
PARSeqType=VL, Backbone=DeiT, Structure=Transformer, Size=32×1282022.0388.9
LevOCRType=VL, Backbone=ResNet45, Structure=ResNet, Size=32×1282022.0388.1
LevOCRType=VL, Backbone=ViT, Structure=Transformer, Size=32×1282022.0388.1
S-GTRType=VL, Backbone=ResNet50Dilated-PPM, Structure=ResNet, Size=64×2562022.0387.9
SIGARType=V, Backbone=ResNet45, Structure=ResNet, Size=32×1282022.0387.1
MORANLexicon=Full2019.0186.7
VisionLANType=VL, Backbone=ResNet45, Structure=ResNet, Size=64×2562022.0386
Bhunia et al.Type=VL, Backbone=ResNet50-FPN, Structure=ResNet, Size=32×1002022.0385.7
SRNType=VL, Backbone=ResNet50-FPN, Structure=ResNet, Size=64×2562022.0385.1
Cheng et al. [6]Lexicon=Full2019.0183.7
Liu et al.Lexicon=Full2019.0183.6
Cheng et al. [5]Lexicon=Full2019.0181.6
Yang et al.Lexicon=Full2019.0180.2
Shi et al.Lexicon=Full2019.0177.4
MORANLexicon=None2019.0176.1
Yang et al.Lexicon=None2019.0175.8
Phan et al.Lexicon=502019.0175.6
Liu et al.Lexicon=None2019.0173.5
Cheng et al. [6]Lexicon=None2019.0173
Shi et al.Lexicon=None2019.0171.8
Cheng et al. [5]Lexicon=None2019.0171.5
Phan et al.Lexicon=Full2019.0167
Mishra et al.Lexicon=502019.0145.7
ABBYY et al.Lexicon=502019.0140.5
Wang et al.Lexicon=502019.0140.2
Wang et al.Lexicon=Full2019.0132.4
ABBYY et al.Lexicon=Full2019.0126.1
Mishra et al.Lexicon=Full2019.0124.7