Zhen Wei | Homepage

I am currently a fourth-year Ph.D student in the 3D Vision lab of the Department of Computer science, University of North Carolina at Chapel Hill. My advisor is Prof. Jan-Michael Frahm. My research interests lie in Computer Vision and Machine Learning.

I obtained my bachelor's degree from Shanghai Jiao Tong University in 2016. I was in ACM Honored Class (a pilot computer science class in China) and did research in BCMI lab supervised by Prof. Hongtao Lu

University of North Carolina at Chapel Hill
2016 - Present, Ph.D Program in Computer Science
Research Assistant: Egocentric Human Pose Estimation

Shanghai Jiao Tong University
2012 - 2016, B.S.E., Computer Science and Technology
ACM Honored Class (a pilot computer science class in China)

Work Experience

I was very fortunate to have interned at Microsoft Reasearch Asia (Beijing, 2015) in Visual Computing Group under supervision of Dr. Jingdong Wang, SAIC Innovation Center (San Jose, 2017) in Autonomous Driving Group supervised by Dr. Jerry Yu, Amazon Robotics in CV/ML Group (Seattle, 2018) and Facebook Research in Mobile Vision Team (Menlo Park, 2019) supervised by Dr.Péter Vajda and Dr. Peizhao Zhang.

Facebook Research
2019.05 - 2019.08, Menlo Park, CA (2019.08 - 2019.12 Part-time)
Research Intern: Video-based Egocentric Human Pose Estimation

Amazon Robotics
2018.05 - 2018.08, Seattle, WA
Applied Scientist Intern: Neural Network Understanding and Interpreting

SAIC Innovation Center
2017.05 - 2017.08
Summer Intern: 3D Object Detection with Image and Lidar Fusion

Microsoft Research Asia
2015.08 - 2016.02
Research Intern: Start the journey of Deep Learning.
Topics: network archtecture, human pose estimation.

Publications and Projects

Egocentric 3D Human Pose Estimation with Head-worn Cameras (New Version of Glasses and Cameras)
2018.10 - 2019.05 (Currently part-time intern in Facebook )
Collabrated with Dongxu Zhao in our lab.

Indoor and mobile capture system
Dataset collection with 3D human pose
Egocentric 3D human pose estimation

Towards Fully Mobile 3D Face, Body, and Environment Capture Using Only Head-worn Cameras
Young-Woon Cha*, True Price*, Zhen Wei, Xinran Lu, Nicholas Rewkowski, Rohan Chabra, Zihe Qin, Hyounghun Kim, Zhaoqi Su, Yebin Liu, Adrian Ilie, Andrei State, Zhenlin Xu, Jan-Michael Frahm, Henry Fuchs
IEEE International Symposium on Mixed and Augmented Reality (ISMAR), 2018
IEEE Transactions on Visualization and Computer Graphics (TVCG), 2018
pdf video

Project: 3D Reconstruction with Semantic Labels using Drone Image Dataset
2018.03 - 2018.10

Semi-supervised semantic segmentation for drone image dataset
3D reconstruction with 2D predicted semantic labels

Augmenting Crowd-Sourced 3D Reconstructions using Semantic Detections
True Price, Johannes Schönberger, Zhen Wei, Marc Pollefeys, Jan-Michael Frahm
CVPR, 2018
pdf supplementary video

Dynamic Visual Sequence Prediction with Motion Flow Networks
Dinghuang Ji, Zhen Wei, Enrique Dunn, Jan-Michael Frahm
WACV, 2018
pdf

Deeply-Fused Nets
Jingdong Wang, Zhen Wei, Ting Zhang, Wenjun Zeng
arXiv:1605.07716
pdf

DisturbLabel: Regularizing CNN on the Loss Layer
Lingxi Xie, Jingdong Wang, Zhen Wei, Meng Wang and Qi Tian
CVPR, 2016
pdf poster slides project

Distance Preserving Marginal Hashing for image retrieval
Li Wu, Kang Zhao, Hongtao Lu, Zhen Wei, Baoliang Lu
IEEE International Conference on Multimedia and Expo (ICME), 2015
pdf