I am a third-year PhD student in Computer Science at University of California, Los Angeles (UCLA). I am working with Professor Stefano Soatto at UCLA Vision Lab. Before joining UCLA, I obtained my B.Sc. in Computer Science from University of Electronic Science and Technology of China (UESTC), Chengdu, P.R. China. I was advised by Professor Shuaicheng Liu and Professor Bing Zeng at UESTC Institute of Image Processing.
My research interests lie in the field of Computer Vision, Machine Learning and Reinforcement Learning. Currently, I am focusing on (3D) Computer Vision and Deep Reinforcement Learning, with applications in 3D object & scene understanding, autonomous driving, and intelligent robotic systems. [RESUME]
- [internship] Got research internship offers from MSR, Adobe Research, Waymo, Amazon Research, Nvidia Research, Megvii (Face++) Research USA, ByteDance AI Lab USA and WeRide.ai.
- [publication] GeoNet: Deep Geodesic Networks for Point Cloud Analysis [PDF] [Project]
- [publication] GIF2Video: Color Dequantization and Temporal Interpolation of GIF Images [PDF] [Project]
- [publication] One paper accepted: AAAI Conference on Artificial Intelligence (AAAI), 2019. [PDF] [Project]
- [preprint] FashionNet: Personalized Outfit Recommendation with Deep Neural Network [PDF] [Project]
- [blog] Posterior Approximation for Variational Inference
- [publication] One paper accepted: International Conference on Image and Graphics (ICIG), 2017. [PDF] [Project]
- [publication] One paper accepted: IEEE Transactions on Image Processing (TIP), 2016. [PDF] [Project]
- [poster] SLAM: Grid-Based Uniform Feature Tracking for Visual-Inertial Navigation [PDF] [Project]