|
I am currently a postdoctoral researcher at Embedded AI and IoT Lab of Department of Information Engineering, CUHK, working with Prof. Guoliang Xing. I obtained my Ph.D. degree from the same department in 2023, advised by Prof. Guoliang Xing. I also work closely with Prof. Xiaoming Liu from Michigan State University. My research interest is building Mobile Sensing/Vision Systems, with a primary focus on advancing the sensing capabilties of Time-of-Flight (ToF) depth cameras. I also have extensive experience in building AI-powered mobile health systems in natural living environments. I won the Best Paper Award of ACM MobiSys in 2023. I also co-founded a startup in Hong Kong named ThingX Technologies and work as CTO to apply AI technologies to daily health monitoring and home care. Email / Google Scholar / LinkedIn / Github |
|
|
|
|
Mozart: A Mobile ToF System for Sensing in the Dark through Phase Manipulation Zhiyuan Xie*, Xiaomin Ouyang* (*co-first authors), Li Pan, Wenrui Lu, Guoliang Xing, Xiaoming Liu[MobiSys 2023] In the 21th Annual International Conference on Mobile Systems, Applications, and Services (Acceptance ratio: 41/198=20.7%) Best Paper Award (1 out of 198 submissions) |
|
UltraDepth: Exposing High-resolution Texture from Depth Cameras Zhiyuan Xie, Xiaomin Ouyang, Xiaoming Liu, Guoliang Xing [SenSys 2021]In the 19th ACM Conference on Embedded Networked Sensor Systems (Acceptance ratio: 25/139=17.9%) |
|
Harmony: Heterogeneous Multi-Modal Federated Learning through Disentangled Model Training Xiaomin Ouyang, Zhiyuan Xie, Heming Fu, Sitong Cheng, Li Pan, Neiwen Ling, Guoliang Xing, Jiayu Zhou, Jianwei Huang [MobiSys 2023] In the 21th Annual International Conference on Mobile Systems, Applications, and Services (Acceptance ratio: 41/198=20.7%) |
|
ClusterFL: A Similarity-Aware Federated Learning System for Human Activity Recognition Xiaomin Ouyang, Zhiyuan Xie, Jiayu Zhou, Jianwei Huang, Guoliang Xing [MobiSys 2021] In the 19th Annual International Conference on Mobile Systems, Applications, and Services (Acceptance ratio: 36/166=21.6%) |