most citedMaskOCR: Text Recognition with Masked Encoder-Decoder Pretraining

24 citations · 24 across the 1 of their papers we have counts for

collaborators

1 paper

cs.CV2022★ 24 cited

MaskOCR: Text Recognition with Masked Encoder-Decoder Pretraining

Pengyuan Lyu, Chengquan Zhang, Shanshan Liu +7

Text images contain both visual and linguistic information. However, existing pre-training techniques for text recognition mainly focus on either visual representation learning or…