Bin Xu

Papers

• MonoFENet: Monocular 3D Object Detection With Feature Enhancement Networks.
  Wentao Bao, Bin Xu, Zhenzhong Chen
  IEEE Transactions on Image Processing (TIP), 2020
  [Paper] [Bibtex]
  

        @inproceedings{BaoXC20,
        title = {MonoFENet: Monocular 3D Object Detection With Feature Enhancement Networks},
        author = {Bao, Wentao and Xu, Bin and Chen, Zhenzhong},
        booktitle = {IEEE TIP},
        year = {2020}}
      

• Multi-Level Fusion based 3D Object Detection from Monocular Images.
  Bin Xu, Zhenzhong Chen
  International Conference on Computer Vision and Pattern Recognition (CVPR), 2018
  [Paper] [Bibtex]
  

        @inproceedings{cvpr18xu,
        title = {Multi-Level Fusion based 3D Object Detection from Monocular Images},
        author = {Xu, Bin and Chen, Zhenzhong},
        booktitle = {IEEE CVPR},
        year = {2018}}
      

• CNN-Based Rate-Distortion Modeling for H.265/HEVC.
  Bin Xu, Xiang Pan, Yan Zhou, Yiming Li, Daiqin Yang, Zhenzhong Chen
  IEEE Visual Communications and Image Processing (VCIP), 2017
  [Paper] [Bibtex]
  

        @inproceedings{vcip17xu, 
        author={Bin, Xu and Xiang, Pan and Yan, Zhou and Yiming, Li and Daiqin, Yang and Zhenzhong, Chen}, 
        booktitle={2017 IEEE Visual Communications and Image Processing (VCIP)}, 
        title={CNN-based rate-distortion modeling for H.265/HEVC}, 
        year={2017}}
      

• Object Tracking over a Multiple-Camera Network.
  Zhenzhong Chen, Weihang Liao, Bin Xu, Hongyi Liu, Qisheng Li, He Li, Chao Xiao, Hang Zhang, Yiming Li, Wentao Bao, Daiqin Yang
  IEEE International Conference on Multimedia Big Data (BigMM), 2015
  [Paper] [Bibtex]
  

        @inproceedings{7153895, 
        author={Zhenzhong, Chen and Weihang, Liao and Bin, Xu and Hongyi, Liu and Qisheng, Li and He, Li and Chao, Xiao and Hang, Zhang and Yiming, Li and Wentao, Bao and Daiqin, Yang}, 
        booktitle={2015 IEEE International Conference on Multimedia Big Data}, 
        title={Object Tracking over a Multiple-Camera Network}, 
        year={2015}}
      

Research

• Deep Learning and 3D Perception: 3D obstacle detection with monocular/stereo images and point cloud.

• Surveillance Video Processing: pedestrian and vehicle detection, tracking, abnormal event detection.

• Deep Learning and Image Coding: CNN-based R-D modeling and its applications.

• Remote Sensing Image Processing: object detection in high resolution remote sensing images.

Experience

• M.S. Photogrammetry and Remote Sensing, School of Remote Sensing and Information Engineering, Wuhan University, September 2015

• B.E. Surveying Engineering, School of Geodesy and Geomatics, Wuhan University, September 2011

Awards

• First Prize, IEEE BigMM 2015 Challenge: “Large-Scale Object Tracking over a Multiple-Camera Network”, 2015

• First-Class Prize, The 14th "Challenge Cup" National Undergraduate Curricular Academic Science and Technology Contest on "Smart City", 2015

• Second-Class Prize, The 3rd National Graduate Contest on Smart-City Technology and Creative Design, Abnormal Event Detection，2016

• Third-Class Prize, The 4th National Graduate Contest on Smart-City Technology and Creative Design, Abnormal Event Detection，2017

• National Scholarship, 2016

• Bronze Award, The 1st Public Opinion Analysis Technology Invitational, Face Recognition, 2016

• Advanced Individual, Wuhan University, 2015

Skills

• Programming: Python, C/C++, Matlab, Java

• Deep Learning: PyTorch, MxNet, TensorFlow, Keras, Caffe/Caffe2