B
Baoguang Shi
Researcher at Huazhong University of Science and Technology
Publications - 31
Citations - 8914
Baoguang Shi is an academic researcher from Huazhong University of Science and Technology. The author has contributed to research in topics: Convolutional neural network & Artificial neural network. The author has an hindex of 22, co-authored 31 publications receiving 6050 citations. Previous affiliations of Baoguang Shi include Microsoft.
Papers
More filters
Journal ArticleDOI
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.
Journal ArticleDOI
AID: A Benchmark Data Set for Performance Evaluation of Aerial Scene Classification
Gui-Song Xia,Jingwen Hu,Fan Hu,Baoguang Shi,Xiang Bai,Yanfei Zhong,Liangpei Zhang,Xiaoqiang Lu +7 more
TL;DR: The Aerial Image Data Set (AID) as mentioned in this paper is a large-scale data set for aerial scene classification, which contains more than 10,000 aerial images from remote sensing images.
Journal ArticleDOI
AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification
TL;DR: The Aerial Image data set (AID), a large-scale data set for aerial scene classification, is described to advance the state of the arts in scene classification of remote sensing images and can be served as the baseline results on this benchmark.
Journal ArticleDOI
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.
Proceedings ArticleDOI
Detecting Oriented Text in Natural Images by Linking Segments
TL;DR: SegLink, an oriented text detection method to decompose text into two locally detectable elements, namely segments and links, achieves an f-measure of 75.0% on the standard ICDAR 2015 Incidental (Challenge 4) benchmark, outperforming the previous best by a large margin.