Ze (Edward) Ma

I am an MSCS student at Columbia University. Before that I finished my bachelor's degree at Shanghai Jiao Tong University, advised by Prof. Chao Ma. I was a research intern at UC Berkley, where I was advised by Prof. Angjoo Kanazawa, Prof. Pieter Abbeel and Prof. Sergey Levine.

My research interests mainly fall in reinforcement learning, computer vision and machine learning system.

Email  /  CV  /  Github

profile photo

Research

AMP: Adversarial Motion Priors for Stylized Physics-Based CharacterControl
Xue Bin Peng*, Ze Ma*, Pieter Abbeel, Sergey Levine, Angjoo Kanazawa
ACM Transactions on Graphics (Proc. SIGGRAPH 2021)

Area: Reinfocement Leanring, Physics-Based Animation

Learning Transferable Kinematic Dictionary for 3D Human Pose and Shape Reconstruction
Ze Ma, Yifan Yao, Pan Ji, Chao Ma
On Arxiv

Area: 3D Human Reconstruction, Sparse Coding

PaStaNet: Toward Human Activity Knowledge Engine
Yong-Lu Li, Liang Xu, Xinpeng Liu, Xijie Huang, Yue Xu, Shiyi Wang, Hao-Shu Fang, Ze Ma, Mingyang Chen, Cewu Lu
CVPR 2020
project page / arXiv

Area: Action Recognition, Few-shot Learning

Transferable Interactiveness Knowledge for Human-Object Interaction Detection
Yong-Lu Li, Siyuan Zhou, Xijie Huang, Liang Xu, Ze Ma, Hao-Shu Fang, Yan-Feng Wang, Cewu Lu
CVPR 2019
arXiv

Area: Action Recognition, Transfer Learning

Thanks to Jon Barron's awesome design!