CVPR 2020

Detection

ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network

Recognition

E2E

Others

Change Log

[20/04/02] Made Issue
[20/04/02] add ABCNet(Detection)

CVPR 2019

Detection

• Arbitrary Shape Scene Text Detection with Adaptive Text Region Representation

Recognition

• Sequence-to-Sequence Domain Adaptation Network for Robust Text Image Recognition

• Aggregation Cross-Entropy for Sequence Recognition
  https://github.com/summerlvsong/Aggregation-Cross-Entropy

• ESIR: End-to-end Scene Text Recognition via Iterative Image Rectification

ETC

Text Effect

• Typography with Decor: Intelligent Text Style Transfer
  https://daooshee.github.io/Typography2019/

Keyword spotting

• An Alternative Deep Feature Approach to Line Level Keyword Spotting

Handwritten

• Handwriting Recognition in Low-resource Scripts using Adversarial Learning
  https://github.com/AyanKumarBhunia/Handwriting_Recogition_using_Adversarial_Learning

Should be http://jiaya.me/papers/textdetection_cvpr19.pdf but instead wrongly linked to https://arxiv.org/pdf/1904.06535.pdf

I think we should add a paper which is named "Detecting Text in Natural Scenes with
Stroke Width Transform",although,it is very early,lots of classical papers mention it.
address:https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/201020CVPR20TextDetection.pdf

ICCV2019

Detection

• Geometry Normalization Networks for Accurate Scene Text Detection
• Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network

Recognition

• What is wrong with scene text recognition model comparisons? dataset and model analysis
  https://github.com/clovaai/deep-text-recognition-benchmark
• Symmetry-constrained Rectification Network for Scene Text Recognition

E2E

• Towards Unconstrained End-to-End Text Spotting
• TextDragon: An End-to-End Framework for Arbitrary Shaped Text Spotting

Etc

• DewarpNet: Single-Image Document Unwarping With Stacked 3D and 2D Regression Networks
• Scene Text Visual Question Answering
• Chinese Street View Text: Large-Scale Chinese Text Reading With Partially Supervised Learning
• GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and Recognition

??

• Convolutional Character Networks
• TextPlace: Visual Place Recognition and Topological Localization Through Reading Scene Texts
• See-Through-Text Grouping for Referring Image Segmentation
• Large-Scale Tag-Based Font Retrieval With Generative Feature Learning

Missing papers

Detection

• cvpr18 Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation PYTORCH(M)

End-to-end recognition means that the whole image is feed into the network and the network will output the recognition result for the whole image.

The input image to the network in ASTER is not the whole image, but a small part containing the warped text. I think it is more proper to call ASTER a recognition algorithm which can deal with irregular text images.

The official Caffe2 implementation of Mask TextSpotter (ECCV 2018) is here:
https://github.com/lvpengyuan/masktextspotter.caffe2

想问一下评价标准P,R是以iou大于0.5为标准计算的吗

A New Unified Method for Detecting Text from Marathon Runners and Sports Players in Video

Has been accepted in Pattern Recognition Journal, Elsevier 2020