List your company
ResearchFormerly WizWand

Scene Text Recognition on Uber

91.6AccuracyViSu
37.20851.32965.4579.571Nov 23, 2024
Updated 8mo ago

Evaluation results

MethodLinks
ViSuDatasets=RL+RU2024.1191.6
ParSeq†Datasets=RL2024.1187.4
CLIP-OCR†Datasets=RL2024.1186.3
LPV†Datasets=RL2024.1181.8
LISTER†Datasets=RL2024.1181.3
MGP†Datasets=RL2024.1180.7
TRBA-cr†Datasets=RL+RU2024.1177.7
Baseline-ViSuTraining Datasets=SL+RU2024.1167.2
BaselineTraining Datasets=SL2024.1160.3
TRBA-ViSuTraining Datasets=SL+RU2024.1158.4
TRBA†Training Datasets=SL2024.1154.7
TRBA-pr*Datasets=RL1+RU12024.1154.2
TRBA-pr*Training Datasets=RL+RU12024.1154.2
LISTER*Training Datasets=SL2024.1149
CRNN-ViSuTraining Datasets=SL+RU2024.1145.9
CRNN-pr*Datasets=RL1+RU12024.1145.2
CRNN-pr*Training Datasets=RL+RU12024.1145.2
CLIP-OCRTraining Datasets=SL2024.1142.4
CRNN†Training Datasets=SL2024.1142.4
ParSeqTraining Datasets=SL2024.1142
MGP*Training Datasets=SL2024.1140.7
TRBA-cr†Training Datasets=SL+RU2024.1140
ABINet*Training Datasets=SL+Wiki+Uber2024.1139.6
TRBA-cr*Training Datasets=SL+RU22024.1139.3