Biograph

Xiaoyuan NI is a fourth-year undergraduate student majoring in Computer Science at the Hong Kong University of Science and Technology (HKUST). He is a passionate researcher in the fields of Machine Learning (ML) and Computer Vision (CV). His research interests include reinforcement learning and video recognition, and devoted to AI applications in the real-world context.

He has rich experience in both the academics and the industry field. He conducted researches in few-shot action recognition under the supervision of Prof. Chi-Keung Tang and conveyed the UROP Program in pedestrian tracking and human reidentification under the supervision of Prof. Shueng-Han Gary Chan. Besides, he worked as a research intern in Microsoft Research Asia (MSRA) and researched the reinforcement learning application in Combinatorial Optimization problems. He worked as a software development intern at Tencent for quality assurance and Fesco Adecco for billing system development.

Research

Cooperative Policy Learning with Pre-trained Heterogeneous Observation Representations
Wenlei Shi, Xinran Wei, Jia Zhang, Xiaoyuan Ni, Arthur Jiang, Jiang Bian and Tie-Yan Liu
Full paper and oral accepted, AAMAS-2021
[Paper] [Project Page] [GitHub]


Semi-Supervised Few-shot Atomic Action Recognition
Xiaoyuan Ni*, Sizhe Song*, Yu-Wing Tai, Chi-Keung Tang
Tech Report.
[Paper] [Project Page] [GitHub]