MaskTextSpotter v2

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision2 results

Text SpottingonInverse-Text
F-measure (%) - Full Lexicon· 2018-07-06
43.5
best: 75.8 (DeepSolo (ViTAEv2-S, TextOCR))
SOTA
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes arXiv:1807.02242
Text SpottingonInverse-Text
F-measure (%) - No Lexicon· 2018-07-06
39
best: 68.8 (DeepSolo (ViTAEv2-S, TextOCR))
SOTA
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes arXiv:1807.02242