activity
20172022
most citedDetecting Curve Text in the Wild: New Dataset and New Solution

212 citations · 341 across the 8 of their papers we have counts for

collaborators

18 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.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.CV2021

ICDAR 2021 Competition on Integrated Circuit Text Spotting and Aesthetic Assessment

Chun Chet Ng, Akmalul Khairi Bin Nazaruddin, Yeong Khang Lee +6

With hundreds of thousands of electronic chip components are being manufactured every day, chip manufacturers have seen an increasing demand in seeking a more efficient and effecti…

cs.CV2021

ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting

Yuliang Liu, Chunhua Shen, Lianwen Jin +4

End-to-end text-spotting, which aims to integrate detection and recognition in a unified framework, has attracted increasing attention due to its simplicity of the two complimentar…

cs.CV202013 cited

On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answering

Xinyu Wang, Yuliang Liu, Chunhua Shen +6

Visual Question Answering (VQA) methods have made incredible progress, but suffer from a failure to generalize. This is visible in the fact that they are vulnerable to learning coi…

cs.CV202037 cited

ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network

Yuliang Liu, Hao Chen, Chunhua Shen +3

Scene text detection and recognition has received increasing research attention. Existing methods can be roughly categorized into two groups: character-based and segmentation-based…