Liang Xu

I am a third-year master student in Machine Vision and Intelligence Group at Shanghai Jiao Tong University, supervised by Prof. Cewu Lu. Currently, I am a research intern in Intelligent Multimedia Group at Microsoft Research Asia, working with Wenjun Zeng and Cuiling Lan.

My research interests mainly fall in human activity modeling, human-centric interaction understanding and related fields, like activity reasoning and robotics.

Email  /  Github  /  Google Scholar


2020.02: One paper PaStaNet is accepted to CVPR 2020.

2019.04: We release our project HAKE: Human Activity Knowledge Engine!

2019.02: One paper Interactiveness is accepted to CVPR 2019.

2018.09: Join Shanghai Jiao Tong University!


Microsoft Research Asia, Beijing, China
Research Intern at Intelligent Multimedia Group, Jul. 2020 - Feb. 2021

Shanghai Jiao Tong University, Shanghai, China
Master of Science and Technology in Computer Science, Sept. 2018 - Mar. 2021

Nanjing University, Nanjing, China
Bachelor of Science in Computer Science, Sept. 2014 - Jun. 2018

Skeleton-Based Mutually Assisted Interacted Object Localization and Human Action Recognition
Liang Xu, Cuiling Lan, Wenjun Zeng, Cewu Lu
Anonymous submission  
Predicate-Aware Learning Network for Visual Relationship Recognition
Liang Xu, Yong-Lu Li, Mingyang Chen, Yan Hao, Cewu Lu,
IEEE International Conference on Multimedia and Expo (ICME), Oral 
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,
[Paper] [Code] [Project]
CVPR, 2020  
3D Objectness Estimation via Bottom-up Regret Grouping
Zelin Ye, Yan Hao, Liang Xu, Rui Zhu, Cewu Lu,
HAKE: Human Activity Knowledge Engine
Yong-Lu Li, Liang Xu, Xijie Huang, Xinpeng Liu, Ze Ma, Mingyang Chen, Shiyi Wang, Hao-Shu Fang, Cewu Lu,
[Paper] [Project]
Transferable Interactiveness Prior 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  

Thanks for the awesome design!