Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/Mask TextSpotter

Mask TextSpotter

Reported on 7 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 Vision7 results

Scene Text DetectiononICDAR 2013
Precision· 2018-07-06
95
best: 97.4 (CRAFT)
SOTA
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes arXiv:1807.02242
Scene Text DetectiononICDAR 2013
Recall· 2018-07-06
88.6
best: 93.1 (CRAFT)
SOTA
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes arXiv:1807.02242
Scene Text DetectiononTotal-Text
Precision· 2018-07-06
69
best: 93 (MixNet)
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes arXiv:1807.02242
Scene Text DetectiononTotal-Text
Recall· 2018-07-06
55
best: 88.1 (MixNet)
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes arXiv:1807.02242
Scene Text DetectiononICDAR 2015
F-Measure· 2018-07-06
86
best: 92.23 (TextFuseNet (ResNeXt-101))
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes arXiv:1807.02242
Scene Text DetectiononICDAR 2015
Precision· 2018-07-06
91.6
best: 93.96 (TextFuseNet (ResNeXt-101))
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes arXiv:1807.02242
Scene Text DetectiononICDAR 2015
Recall· 2018-07-06
81
best: 91.98 (CharNet H-88 (single-scale))
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes arXiv:1807.02242