Text Spotting
52 papers with code • 4 benchmarks • 6 datasets
Text Spotting is the combination of Scene Text Detection and Scene Text Recognition in an end-to-end manner. It is the ability to read natural text in the wild.
Benchmarks
These leaderboards are used to track progress in Text Spotting
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Text Spotting models and implementationsDatasets
Total-Text
ICDAR 2015
SCUT-CTW1500
LSVTD
Most implemented papers
Open Images V5 Text Annotation and Yet Another Mask Text Spotter
openvinotoolkit/training_extensions
•
•
A large scale human-labeled dataset plays an important role in creating high quality deep learning models.
SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition
mxin262/swintextspotter
•
•
CVPR 2022
End-to-end scene text spotting has attracted great attention in recent years due to the success of excavating the intrinsic synergy of the scene text detection and recognition.
GLASS: Global to Local Attention for Scene-Text Spotting
amazon-research/glass-text-spotting
•
•
In recent years, the dominant paradigm for text spotting is to combine the tasks of text detection and recognition into a single end-to-end framework.
DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting
vitae-transformer/deepsolo
•
•
CVPR 2023
In this paper, we present DeepSolo, a simple DETR-like baseline that lets a single Decoder with Explicit Points Solo for text detection and recognition simultaneously.
DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting
vitae-transformer/deepsolo
•
•
In this paper, we present DeepSolo++, a simple DETR-like baseline that lets a single decoder with explicit points solo for text detection, recognition, and script identification simultaneously.
Bridging the Gap Between End-to-End and Two-Step Text Spotting
mxin262/bridging-text-spotting
•
•
Subsequently, we introduce a Bridge that connects the locked detector and recognizer through a zero-initialized neural network.
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes
lvpengyuan/masktextspotter.caffe2
•
•
ECCV 2018
Recently, models based on deep neural networks have dominated the fields of scene text detection and recognition.
Visual Semantic Re-ranker for Text Spotting
ahmedssabir/Visual-Semantic-Relatedness-with-Word-Embedding
•
•
In this paper, we propose a post-processing approach to improve the accuracy of text spotting by using the semantic relation between the text and the scene.
You Only Recognize Once: Towards Fast Video Text Spotting
hikopensource/davar-lab-ocr
•
•
Video text spotting is still an important research topic due to its various real-applications.
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes
MhLiao/MaskTextSpotter
•
•
ECCV 2018
Moreover, we further investigate the recognition module of our method separately, which significantly outperforms state-of-the-art methods on both regular and irregular text datasets for scene text recognition.
