Xiaozhi Chen
Research
  • My research interests lie in computer vision and machine learning, with particular interest in 2D/3D object detection and its applications on autonomous driving. I am supervised by Prof. Huimin Ma.
  • Jan. 2015 - May. 2015, visited Machine Learning Group at University of Toronto, woking with Raquel Urtasun and Sanja Fidler.
Publications
Dummy Image

Multi-View 3D Object Detection Network for Autonomous Driving
Xiaozhi Chen, Huimin Ma, Ji Wan, Bo Li, Tian Xia
International Conference on Computer Vision and Pattern Recognition (CVPR), 2017 (Spotlight)
[Paper][BibTex][Demo(52M)][3D Evaluation Code]
KITTI train/val split used in 3DOP/Mono3D/MV3D

Dummy Image

Monocular 3D Object Detection for Autonomous Driving
Xiaozhi Chen, Kaustav Kunku, Ziyu Zhang, Huimin Ma, Sanja Fidler, Raquel Urtasun
International Conference on Computer Vision and Pattern Recognition (CVPR), 2016
[Paper][Supplement][Project Page][Demo][KITTI Results][BibTex]

Dummy Image

3D Object Proposals for Accurate Object Class Detection
Xiaozhi Chen*, Kaustav Kunku*, Yukun Zhu, Andrew Berneshawi, Huimin Ma, Sanja Fidler, Raquel Urtasun
Neural Information Processing Systems (NIPS), 2015
[Paper][Supplement][Project Page][Demo][KITTI Results][BibTex]
* Denotes equal contribution

Dummy Image

Geodesic Weighted Bayesian Model for Salient Object Detection
Xiang Wang, Huimin Ma, Xiaozhi Chen
International Conference on Image Processing (ICIP), 2015 (Oral)
[Paper] [Project Page] [BibTex]

Dummy Image

Improving Object Proposals with Multi-Thresholding Straddling Expansion
Xiaozhi Chen, Huimin Ma, Xiang Wang, Zhichen Zhao
International Conference on Computer Vision and Pattern Recognition (CVPR), 2015
[Paper] [Project Page] [BibTex]

Dummy Image

Learning a Compact Latent Representation of the Bag-of-Parts Model
Xiaozhi Chen, Huimin Ma
International Conference on Image Processing (ICIP), 2014
[Paper] [BibTex]

Patents
  1. Huimin Ma, Xiaozhi Chen, Shangfu Ouyang, Wenyu Li, and Shurui Bao. Image Cognition Psychoanalysis System. CN Patent, CN201310221563, 2013.