EATEN icon indicating copy to clipboard operation
EATEN copied to clipboard

EATEN: Entity-aware Attention for Single Shot Visual Text Extraction

Results 7 EATEN issues
Sort by recently updated
recently updated
newest added

I'm working in a similar research area, and it would be really interesting to see the details around implementation. Would you consider open sourcing or sharing the code? My e-mail...

How the dataset should be prepared? The ground truth labels and images

could you open the source code? I really like yours work! This is my email:[email protected] Thank you!

Thank you for sharing the data. It's very helpful. In your "todo" list, you mentioned, "Use CycleGan or domain adaptation to synth data to train EATEN." The current generation results...

Thanks for your great repo If I have passport image, how to transform my image to the same image in eaten?? Thank you

车票数据好像只包含合成的300k和测试的400张真实