List your company
ResearchFormerly WizWand

Scene Text Recognition on IC13

97.7AccuracyABINet-LVest
88.23690.69393.1595.607May 22, 2020Nov 26, 2020Jun 3, 2021Dec 9, 2021Jun 16, 2022Dec 22, 2022Jun 29, 2023
Updated 8mo ago

Evaluation results

MethodLinks
ABINet-LVestLabeled Datasets=MJ+ST, Unlabeled Datasets=Uber-Text2021.0397.7
ABINet-LVLabeled Datasets=MJ+ST2021.0397.4
ABINetTraining Datasets=MJ and ST2023.0697.4
ABINet-LVstLabeled Datasets=MJ+ST, Unlabeled Datasets=Uber-Text2021.0397.3
DiffusionSTRTraining Datasets=MJ and ST2023.0697.1
PARSeqTraining Datasets=MJ and ST2023.0697
ABINet-SVLabeled Datasets=MJ+ST2021.0396.8
SRN-LV (Reproduced)Labeled Datasets=MJ+ST2021.0396.8
Our model2021.0796.8
SRN-SV (Reproduced)Labeled Datasets=MJ+ST2021.0396.3
S-Attn/CTC + LMRect.=No, Encoder/Decoder=S-Attn/CTC + LM, Train Dataset=Internal2021.0495.98
SRNLabeled Datasets=MJ+ST2021.0395.5
Yu et al.Rect.=No, Encoder/Decoder=Attn / Semantic Attn., Train Dataset=MJ + ST2021.0495.5
SAMLabeled Datasets=MJ+ST2021.0395.3
Lu et al.Rect.=No, Encoder/Decoder=Global Context Attn / Tfmr Dec., Train Dataset=MJ + ST + SA2021.0495.3
S-Attn/CTC + LMRect.=No, Encoder/Decoder=S-Attn/CTC + LM, Train Dataset=Internal + Public2021.0495.25
RobustScannerLabeled Datasets=MJ+ST2021.0394.8
SCATTERRect.=Yes, Encoder/Decoder=CNN / BiLSTM, Train Dataset=MJ + ST + SA2021.0494.7
RCEED2021.0794.7
S-Attn/CTCRect.=No, Encoder/Decoder=S-Attn/CTC, Train Dataset=Internal2021.0494.43
Bai et al. [2]*lexicon=lexicon-free, training_annotations=word-level and character-level2020.0594.4
TransformerRect.=No, Encoder/Decoder=Transformer, Train Dataset=Internal2021.0494.34
SATRN2021.0794.1
Liu et al. [29]lexicon=lexicon-free, training_annotations=word-level2020.0594
TransformerRect.=No, Encoder/Decoder=Transformer, Train Dataset=Internal + Public2021.0493.97
Yang et al. [53]*lexicon=lexicon-free, training_annotations=word-level and character-level2020.0593.9
DANLabeled Datasets=MJ+ST2021.0393.9
Wang et al.Rect.=No, Encoder/Decoder=FCN/GRU, Train Dataset=MJ + ST2021.0493.9
SCATTERVenue=CVPR’20, Training Set=MJ+ST+Extra, RNN=Y, FPS=-2022.0493.9
DANVenue=AAAI’20, Training Set=MJ+ST, RNN=Y, FPS=-2022.0493.9
TransformerRect.=No, Encoder/Decoder=Transformer, Train Dataset=MJ + ST + Public2021.0493.88
S-Attn/CTCRect.=No, Encoder/Decoder=S-Attn/CTC, Train Dataset=Internal + Public2021.0493.7
S-Attn/CTC + LMRect.=No, Encoder/Decoder=S-Attn/CTC + LM, Train Dataset=MJ + ST + Public2021.0493.61
Bleeker and de RijkeRect.=No, Encoder/Decoder=Transformer, Train Dataset=MJ + ST2021.0493.4
Cheng et al. [7]*lexicon=lexicon-free, training_annotations=word-level and character-level2020.0593.3
Qiao et al.Rect.=No, Encoder/Decoder=LSTM/LSTM + Attn, Train Dataset=MJ + ST2021.0493.3
CSTR2021.0793.2
ASTER2021.0793.2
ViTSTRTraining Datasets=MJ and ST2023.0693.2
Liu et al. [30]*lexicon=lexicon-free, training_annotations=word-level and character-level2020.0592.9
TextscannerLabeled Datasets=MJ+ST2021.0392.9
TextScanner*Venue=AAAI’20, Training Set=MJ+ST+Extra, RNN=N, FPS=-2022.0492.9
SE-ASTER (Ours)lexicon=lexicon-free, training_annotations=word-level2020.0592.8
SE-ASTERLabeled Datasets=MJ+ST2021.0392.8
SEED2021.0792.8
SEEDVenue=CVPR’20, Training Set=MJ+ST, RNN=Y, FPS=-2022.0492.8
ParallelLabeled Datasets=MJ+ST2021.0392.7
Luo et al. [32]lexicon=lexicon-free, training_annotations=word-level2020.0592.4
Baek et al.2021.0792.3
Comb.BestVenue=ICCV’19, Training Set=MJ+ST, RNN=Y, FPS=36.232022.0492.3
Ours-LargeVenue=-, Training Set=MJ+ST, RNN=N, FPS=66.91/255+2022.0492.21
S-Attn/CTCRect.=No, Encoder/Decoder=S-Attn/CTC, Train Dataset=MJ + ST + Public2021.0492.15
ASTER [45]lexicon=lexicon-free, training_annotations=word-level2020.0591.8
Sheng et al.Rect.=Yes, Encoder/Decoder=S-Attn/ Attn, Train Dataset=MJ + ST2021.0491.8
Liao et al. [25]*lexicon=lexicon-free, training_annotations=word-level and character-level2020.0591.5
CA-FCN*Venue=AAAI’19, Training Set=ST, RNN=N, FPS=452022.0491.4
Zhan et al. [57]lexicon=lexicon-free, training_annotations=word-level2020.0591.3
Liu et al. [28]*lexicon=lexicon-free, training_annotations=word-level and character-level2020.0591.1
Li et al. [23]lexicon=lexicon-free, training_annotations=word-level2020.0591
ASTER baseline reproducedlexicon=lexicon-free, training_annotations=word-level2020.0590.9
Lee et al. [22]lexicon=lexicon-free, training_annotations=word-level2020.0590
Shi et al.Rect.=Yes, Encoder/Decoder=LSTM/LSTM + Attn, Train Dataset=MJ + ST2021.0489.75
Shi et al. [43]lexicon=lexicon-free, training_annotations=word-level2020.0589.6
CRNNTraining Datasets=MJ and ST2023.0689.4
RosettaVenue=KDD’18, Training Set=MJ+ST, RNN=N, FPS=212.762022.0489
Shi et al. [44]lexicon=lexicon-free, training_annotations=word-level2020.0588.6