activity
20152022
most citedDetecting Curve Text in the Wild: New Dataset and New Solution

212 citations · 553 across the 36 of their papers we have counts for

collaborators

55 papers

cs.CV20223 cited

MSDS: A Large-Scale Chinese Signature and Token Digit String Dataset for Handwriting Verification

Peirong Zhang, Jiajia Jiang, Yuliang Liu +1

Although online handwriting verification has made great progress recently, the verification performances are still far behind the real usage owing to the small scale of the dataset…

cs.CV20225 cited

Look Closer to Supervise Better: One-Shot Font Generation via Component-Based Discriminator

Yuxin Kong, Canjie Luo, Weihong Ma +4

Automatic font generation remains a challenging research issue due to the large amounts of characters with complicated structures. Typically, only a few samples can serve as the st…

cs.CV20222 cited

SimAN: Exploring Self-Supervised Representation Learning of Scene Text via Similarity-Aware Normalization

Canjie Luo, Lianwen Jin, Jingdong Chen

Recently self-supervised representation learning has drawn considerable attention from the scene text recognition community. Different from previous studies using contrastive learn…

cs.CV20221 cited

SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition

Mingxin Huang, Yuliang Liu, Zhenghao Peng +6

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. How…

cs.CL20222 cited

LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding

Jiapeng Wang, Lianwen Jin, Kai Ding

Structured document understanding has attracted considerable attention and made significant progress recently, owing to its crucial role in intelligent document processing. However…

cs.CV20221 cited

SLOGAN: Handwriting Style Synthesis for Arbitrary-Length and Out-of-Vocabulary Text

Canjie Luo, Yuanzhi Zhu, Lianwen Jin +2

Large amounts of labeled data are urgently required for the training of robust text recognizers. However, collecting handwriting data of diverse styles, along with an immense lexic…