Chong Wang

Chong Wang

Associate Professor

Ningbo University

Biography

Chong Wang received his B. Eng degree from Zhejiang University of Technology in 2007, M. Eng degree from University of Science and Technology of China in 2010, and his Ph.D. degree from The University of Hong Kong in 2014. He was a research assistant and research associate in The University of Hong Kong and Hong Kong Polytechnic University, respectively. Since 2015, he has been with the Faculty of Electrical Engineering and Computer Science, Ningbo University, where he is currently an associate professor.

His main research interests are in gesture recognition, human computer interaction, pattern recognition, image and video restoration and image based rendering

Interests
  • Human-Computer Interaction
  • Image/Video Processing
  • Artificial intelligence
  • Deep Learning
Education

  • PhD in Electrical and Electronic Engineering, 2014

    The Hong Kong University

  • M.Eng in Electronic Engineering and Information Science, 2010

    University of Science and Technology of China

  • B.Eng in Communication Engineering (Jianxing Honors College), 2007

    Zhejiang University of Technology

Projects

基于超像/体素图的手势识别方法

基于超像/体素图的手势识别方法

本项目主要围绕手势数据预处理，静、动态手势特征提取和距离度量，实时手势交互应用这三个方面展开研究。

手势识别 超像素 超体素
基于长短时域特征的动态手势识别方法

基于长短时域特征的动态手势识别方法

在时域引入注意力机制，利用三维卷积网络和时间卷积网络分别提取短时和长时动态手势特征，进而构建高精度的动态手势识别算法。

手势识别 时域卷积网络 三维卷积网络
2-4路360度环视技术

2-4路360度环视技术

2-4路视频全景拼接系统基于时序图像利用之前时刻的图像填充当前相机的盲区部分，从而实现360度环视的效果。

全景拼接 相机矫正 RANSAC

Meet the Team

Researchers

Avatar

Chong Wang

Associate Professor

Human-Computer Interaction, Image/Video Processing, Artificial intelligence, Deep Learning

Grad Students

Avatar

Qiaomei Mao

Master Student

Zero-Shot Learning, Object Detection

Avatar

Shenghao Yu

Master Student

Action Recognition, Deep Learning

Recent Publications

Cross-Epoch Learning for Weakly Supervised Anomaly Detection in Surveillance Videos
In this work, a cross-epoch learning (XEL) strategy associated with a hard instance bank (HIB) is proposed to introduce additional information from previous training epochs.
Cite Code Project DOI
Cross-Epoch Learning for Weakly Supervised Anomaly Detection in Surveillance Videos
Extended Guided Image Filtering For Contrast Enhancement
In this paper, we propose an extended GIF (EGIF) by incorporating a novel edge-aware factor into the regularization term.
Cite DOI IEEE Xplore
Extended Guided Image Filtering For Contrast Enhancement
Reweighted Dynamic Group Convolution
In this paper, a new reweighted dynamic group convolution (RDGC) structure, including a reweighted pruning module and a survival loss, is proposed in this work for more precise channel pruning.
Cite IEEE Xplore
Reweighted Dynamic Group Convolution
A Unified Approach for Target Direction Finding based on Convolutional Neural Networks
In this paper, a convolutional neural network (CNNs) based approach for target direction finding with the thinned coprime array (TCA) as an example is proposed.
Cite DOI IEEE Xplore
A Unified Approach for Target Direction Finding based on Convolutional Neural Networks
Zero-Shot Object Detection with Attributes based Category Similarity
This brief proposes a new algorithm using attributes based category similarity for accurate alignment between visual features and semantic concepts.
Cite DOI
Zero-Shot Object Detection with Attributes based Category Similarity
See all

Recent Posts

Popular Topics

Contrast Enhancement DenseNet DOA EMD距离 Entropy-Variance Domain Guided Image Filtering Kinect RANSAC Thinned Coprime A 三维卷积网络 全景拼接 分组卷积 半监督学习 卷积神经网络 图像增强 图像恢复 基于图像的渲染(IBR) 手势识别 超像素 超像素图