List your company

Scene Text Recognition on Street View Text 647

95.1AccuracySIGAT
86.05288.40190.7593.099Mar 7, 2022

Evaluation results

MethodLinks
SIGATBackbone=ViT-B, Structure=Transformer, Size=32×1282022.0395.1
MGP-STRBackbone=ViT-B, Structure=Transformer, Size=32×128, Venue=ECCV20222022.0394.7
Corner TransformerBackbone=SATRN, Structure=Transformer, Size=32×128, Venue=ECCV20222022.0394.6
PREN2DBackbone=EfficientNet-B3, Structure=CNN, Size=64×256, Venue=CVPR20212022.0394
SIGAsBackbone=SVTR-L, Structure=Transformer*, Size=48×1602022.0393.7
SIGARBackbone=ResNet45, Structure=CNN, Size=32×1282022.0392.7
PlugNetBackbone=ResNet37, Structure=CNN, Size=32×100, Venue=ECCV20202022.0392.3
ABINet+ConCLR+Backbone=ResNet45-Trns, Structure=Transformer, Size=32×128, Venue=AAAI20222022.0392.1
SVTRBackbone=SVTR-L, Structure=Transformer*, Size=48×160, Venue=IJCAI20222022.0391.7
ABINetBackbone=ResNet45-Trns, Structure=Transformer, Size=32×128, Venue=CVPR20212022.0391.7
PIMNetBackbone=ResNet50-FPN, Structure=CNN, Size=64×256, Venue=ACM MM20212022.0391.2
S-GTR+Backbone=ResNet50Dilated-PPM, Structure=CNN, Size=64×256, Venue=AAAI20222022.0391.2
LevOCRBackbone=ResNet45, Structure=CNN, Size=32×128, Venue=ECCV20222022.0390.6
TextScannerBackbone=ResNet50, Structure=CNN, Size=64×256, Venue=AAAI20202022.0390.1
Text is TextBackbone=ResNet31, Structure=CNN, Size=48×160, Venue=ICCV20212022.0389.9
DANBackbone=ResNet45, Structure=CNN, Size=32×128, Venue=AAAI20202022.0389.2
LevOCRBackbone=ViT, Structure=Transformer, Size=32×128, Venue=ECCV20222022.0389.2
SGBANetBackbone=ResNet45-FPN, Structure=CNN, Size=64×256, Venue=ECCV20222022.0389.1
TRBABackbone=ResNet31, Structure=CNN, Size=32×100, Venue=CVPR20212022.0388.9
SRNBackbone=ResNet50-FPN, Structure=CNN, Size=64×256, Venue=CVPR20202022.0388.1
ViTSTRBackbone=ViT-B, Structure=Transformer, Size=224×224, Venue=ICDAR20212022.0387.7
CA-FCNBackbone=VGG16, Structure=CNN, Size=64×256, Venue=AAAI20192022.0386.4