212 citations · 1k across the 74 of their papers we have counts for
7 papers · 1 filter
Improving Attention-Based Handwritten Mathematical Expression Recognition with Scale Augmentation and Drop Attention
Zhe Li, Lianwen Jin, Songxuan Lai +1
Handwritten mathematical expression recognition (HMER) is an important research direction in handwriting recognition. The performance of HMER suffers from the two-dimensional struc…
Joint Layout Analysis, Character Detection and Recognition for Historical Document Digitization
Weihong Ma, Hesuo Zhang, Lianwen Jin +3
In this paper, we propose an end-to-end trainable framework for restoring historical documents content that follows the correct reading order. In this framework, two branches named…
Text Recognition in the Wild: A Survey
Xiaoxue Chen, Lianwen Jin, Yuanzhi Zhu +2
The history of text can be traced back over thousands of years. Rich and precise semantic information carried by text is important in a wide range of vision-based application scena…
Learn to Augment: Joint Data Augmentation and Network Optimization for Text Recognition
Canjie Luo, Yuanzhi Zhu, Lianwen Jin +1
Handwritten text and scene text suffer from various shapes and distorted patterns. Thus training a robust recognition model requires a large amount of data to cover diversity as mu…
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…
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…
Separating Content from Style Using Adversarial Learning for Recognizing Text in the Wild
Canjie Luo, Qingxiang Lin, Yuliang Liu +2
We propose to improve text recognition from a new perspective by separating the text content from complex backgrounds. As vanilla GANs are not sufficiently robust to generate seque…