Improving Structured Text Recognition with Regular Expression Biasing

no code implementations • 10 Nov 2021 • Baoguang Shi, WenFeng Cheng, Yijuan Lu, Cha Zhang, Dinei Florencio

We study the problem of recognizing structured text, i. e. text that follows certain formats, and propose to improve the recognition accuracy of structured text by specifying regular expressions (regexes) for biasing.

Decoder

Progressive and Aligned Pose Attention Transfer for Person Image Generation

1 code implementation • 22 Mar 2021 • Zhen Zhu, Tengteng Huang, Mengde Xu, Baoguang Shi, Wenqing Cheng, Xiang Bai

This paper proposes a new generative adversarial network for pose transfer, i. e., transferring the pose of a given person to a target pose.

Data Augmentation Generative Adversarial Network +2

ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard

no code implementations • 20 Dec 2019 • Xi Liu, Rui Zhang, Yongsheng Zhou, Qianyi Jiang, Qi Song, Nan Li, Kai Zhou, Lei Wang, Dong Wang, Minghui Liao, Mingkun Yang, Xiang Bai, Baoguang Shi, Dimosthenis Karatzas, Shijian Lu, C. V. Jawahar

21 teams submit results for Task 1, 23 teams submit results for Task 2, 24 teams submit results for Task 3, and 13 teams submit results for Task 4.

Line Detection Task 2

Progressive Pose Attention Transfer for Person Image Generation

2 code implementations • CVPR 2019 • Zhen Zhu, Tengteng Huang, Baoguang Shi, Miao Yu, Bofei Wang, Xiang Bai

This paper proposes a new generative adversarial network for pose transfer, i. e., transferring the pose of a given person to a target pose.

Generative Adversarial Network Person Re-Identification +1

ASTER: An Attentional Scene Text Recognizer with Flexible Rectification

4 code implementations • good 2018 • Baoguang Shi, Mingkun Yang, Xinggang Wang, Pengyuan Lyu, Cong Yao, and Xiang Bai

SCENE text recognition has attracted great interest from the academia and the industry in recent years owing to its importance in a wide range of applications.

Optical Character Recognition Optical Character Recognition (OCR) +1

Rotation-Sensitive Regression for Oriented Scene Text Detection

no code implementations • CVPR 2018 • Minghui Liao, Zhen Zhu, Baoguang Shi, Gui-Song Xia, Xiang Bai

Previous methods rely on shared features for both tasks, resulting in degraded performance due to the incompatibility of the two tasks.

Classification General Classification +6

TextBoxes++: A Single-Shot Oriented Scene Text Detector

3 code implementations • 9 Jan 2018 • Minghui Liao, Baoguang Shi, Xiang Bai

In this paper, we present an end-to-end trainable fast scene text detector, named TextBoxes++, which detects arbitrary-oriented scene text with both high accuracy and efficiency in a single network forward pass.

object-detection Object Detection +3

ICDAR2017 Competition on Reading Chinese Text in the Wild (RCTW-17)

5 code implementations • 31 Aug 2017 • Baoguang Shi, Cong Yao, Minghui Liao, Mingkun Yang, Pei Xu, Linyan Cui, Serge Belongie, Shijian Lu, Xiang Bai

This report introduces RCTW, a new competition that focuses on Chinese text reading.

valid

Detecting Oriented Text in Natural Images by Linking Segments

6 code implementations • CVPR 2017 • Baoguang Shi, Xiang Bai, Serge Belongie

It achieves an f-measure of 75. 0% on the standard ICDAR 2015 Incidental (Challenge 4) benchmark, outperforming the previous best by a large margin.

Curved Text Detection Text Detection

TextBoxes: A Fast Text Detector with a Single Deep Neural Network

3 code implementations • 21 Nov 2016 • Minghui Liao, Baoguang Shi, Xiang Bai, Xinggang Wang, Wenyu Liu

This paper presents an end-to-end trainable fast scene text detector, named TextBoxes, which detects scene text with both high accuracy and efficiency in a single network forward pass, involving no post-process except for a standard non-maximum suppression.

AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification

1 code implementation • 18 Aug 2016 • Gui-Song Xia, Jingwen Hu, Fan Hu, Baoguang Shi, Xiang Bai, Yanfei Zhong, Liangpei Zhang

The goal of AID is to advance the state-of-the-arts in scene classification of remote sensing images.

Aerial Scene Classification Classification +2

Deep FisherNet for Object Classification

no code implementations • 31 Jul 2016 • Peng Tang, Xinggang Wang, Baoguang Shi, Xiang Bai, Wenyu Liu, Zhuowen Tu

Our proposed FisherNet combines convolutional neural network training and Fisher Vector encoding in a single end-to-end structure.

Classification Computational Efficiency +3

Robust Scene Text Recognition with Automatic Rectification

5 code implementations • CVPR 2016 • Baoguang Shi, Xinggang Wang, Pengyuan Lyu, Cong Yao, Xiang Bai

We show that the model is able to recognize several types of irregular text, including perspective text and curved text.

Optical Character Recognition (OCR) Scene Text Detection +1

An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition

85 code implementations • 21 Jul 2015 • Baoguang Shi, Xiang Bai, Cong Yao

In this paper, we investigate the problem of scene text recognition, which is among the most important and challenging tasks in image-based sequence recognition.

Optical Character Recognition (OCR) Scene Text Recognition

Automatic Script Identification in the Wild

no code implementations • 12 May 2015 • Baoguang Shi, Cong Yao, Chengquan Zhang, Xiaowei Guo, Feiyue Huang, Xiang Bai

With the rapid increase of transnational communication and cooperation, people frequently encounter multilingual scenarios in various situations.

General Classification Image Classification

Deep Regression for Face Alignment

no code implementations • 18 Sep 2014 • Baoguang Shi, Xiang Bai, Wenyu Liu, Jingdong Wang

In this paper, we present a deep regression approach for face alignment.

Face Alignment regression

Strokelets: A Learned Multi-Scale Representation for Scene Text Recognition

no code implementations • CVPR 2014 • Cong Yao, Xiang Bai, Baoguang Shi, Wenyu Liu

Driven by the wide range of applications, scene text detection and recognition have become active research topics in computer vision.

Scene Text Detection Scene Text Recognition +1