no code implementations • 26 Feb 2020 • Hongyu Wang, Guangcun Shan
In this paper, a robust multiscale neural network is proposed to recognize handwritten mathematical expressions and output LaTeX sequences, which can effectively and correctly focus on where each step of output should be concerned and has a positive effect on analyzing the two-dimensional structure of handwritten mathematical expressions and identifying different mathematical symbols in a long expression.
no code implementations • 22 Jul 2019 • Guangcun Shan, Hongyu Wang, Wei Liang, Congcong Liu, Qizi Ma, Quan Quan
Recently, deep learning technology have been extensively used in the field of image recognition.
no code implementations • 15 Jun 2019 • Tian Wang, Shiye Lei, Youyou Jiang, Choi Chang, Hichem Snoussi, Guangcun Shan
It is found that, compared to the traditional Parameter Server architecture, our parallel architecture has higher efficiency on temporal action detection task with multiple GPUs, which is suitable for dealing with the tasks of temporal action proposal generation, especially for large datasets of millions of videos.
no code implementations • 28 Mar 2019 • Tian Wang, Zichen Miao, Yuxin Chen, Yi Zhou, Guangcun Shan, Hichem Snoussi
It is challenging to detect the anomaly in crowded scenes for quite a long time.
no code implementations • 9 Feb 2019 • Weikuang Li, Tian Wang, Chuanyun Wang, Guangcun Shan, Mengyi Zhang, Hichem Snoussi
Our approach contains a detection module and a module for classification.
no code implementations • 8 Feb 2019 • Guangcun Shan, Hongyu Wang, Wei Liang
Offline handwritten mathematical expression recognition is a challenging task, because handwritten mathematical expressions mainly have two problems in the process of recognition.