GitHub - CVI-SZU/STKM: Self-attention based Text Knowledge Mining for Text Detection (original) (raw)

Skip to content

Navigation Menu

• • AI CODE CREATION
    * GitHub CopilotWrite better code with AI
    * GitHub SparkBuild and deploy intelligent apps
    * GitHub ModelsManage and compare prompts
    * MCP RegistryNewIntegrate external tools

View all features

• Pricing

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Sign up

Appearance settings

• README
• Apache-2.0 license

STKM: Self-attention based Text Knowledge Mining for Text Detection

This is the pytorch implementation of Paper: Self-attention based Text Knowledge Mining for Text Detection (CVPR 2021).

Model

The pre-trained model is now available.

• Baidu Yun password: 5sea
• Google Driver

Installation

• Python=3.8
• PyTorch=1.8.0, torchvision=0.9.0, cudatoolkit=10.2
• OpenCV for visualization

Train

Test

Transfer and replace

Reference

If you find STKM useful in your research, please cite it in your publications:

@inproceedings{wan2021self,
  title={Self-attention based text knowledge mining for text detection},
  author={Wan, Qi and Ji, Haoqin and Shen, Linlin},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={5983--5992},
  year={2021}
}