121 Papers
914 Citations
Cong Yao is an academic researcher from Huazhong University of Science and Technology. The author has contributed to research in topics: Computer science & Object detection. The author has an hindex of 40, co-authored 112 publications. Previous affiliations of Cong Yao include Peking University & Nanjing University.
Chat about Author
Papers
An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition
Baoguang Shi,Xiang Bai,Cong Yao +2 more
TL;DR: Zhang et al. as mentioned in this paper proposed a novel neural network architecture, which integrates feature extraction, sequence modeling and transcription into a unified framework, and achieved remarkable performances in both lexicon free and lexicon-based scene text recognition tasks.
3.2K
EAST: An Efficient and Accurate Scene Text Detector
Xinyu Zhou,Cong Yao,He Wen,Yuzhi Wang,Shuchang Zhou,He Weiran,Jiajun Liang +6 more
- 01 Jul 2017
TL;DR: This work proposes a simple yet powerful pipeline that yields fast and accurate text detection in natural scenes, and significantly outperforms state-of-the-art methods in terms of both accuracy and efficiency.
•Posted Content
EAST: An Efficient and Accurate Scene Text Detector
TL;DR: This paper proposed a simple yet powerful pipeline that yields fast and accurate text detection in natural scenes, eliminating unnecessary intermediate steps (e.g., candidate aggregation and word partitioning) with a single neural network.
1K
ASTER: An Attentional Scene Text Recognizer with Flexible Rectification
TL;DR: This work introduces ASTER, an end-to-end neural network model that comprises a rectification network and a recognition network that predicts a character sequence directly from the rectified image.
987
Detecting texts of arbitrary orientations in natural images
Cong Yao,Xiang Bai,Wenyu Liu,Yi Ma,Zhuowen Tu +4 more
- 16 Jun 2012
TL;DR: A system which detects texts of arbitrary orientations in natural images using a two-level classification scheme and two sets of features specially designed for capturing both the intrinsic characteristics of texts to better evaluate its algorithm and compare it with other competing algorithms.