Liang Xu (徐良)
Currently, I am a computer vision researcher at Sensetime Group Limited.
Prior to Sensetime, I received the M.S. from Shanghai Jiao Tong University in 2021, supervised by Cewu Lu, and the B.S. from Nanjing University in 2018.
I was also fortunate to work with Wenjun Zeng and Cuiling Lan as a research intern in Intelligent Multimedia Group at Microsoft Research Asia.
I have broad research interests on human-centric topics, including modeling the human body, human motion, human activity and human-object interaction.
Email  / 
Github  / 
Google Scholar
|
|
News
2022.04: One paper on skeleton-based action recognition is accepted to IEEE TMM 2022.
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!
|
Experience
SenseTime Technology Development Co., Ltd., Shanghai, China
Computer Vision Researcher, Jun. 2021 - Present
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
IEEE Transactions on Multimedia ( IEEE TMM 2022)  
[Paper]
|
|
PAL-Net: 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 2021), 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,
Computer Vision and Pattern Recognition ( CVPR 2020)  
[Paper] [Code] [Project]
|
Thanks for the awesome design!
|