activity
20212026
most citedTraditional Chinese Synthetic Datasets Verified with Labeled Data for Scene Text Recognition

4 citations · 5 across the 3 of their papers we have counts for

collaborators
Showing 2022Show all

1 paper · 1 filter

cs.CV2022★ 1 cited

SMILE: Sequence-to-Sequence Domain Adaption with Minimizing Latent Entropy for Text Image Recognition

Yen-Cheng Chang, Yi-Chang Chen, Yu-Chuan Chang +1

Training recognition models with synthetic images have achieved remarkable results in text recognition. However, recognizing text from real-world images still faces challenges due…