Currently, I am a postdoctoral researcher at the University of California, Los Angeles, under the supervision of Song-Chun Zhu. Before that, I received the B.S. degree in machine intelligence at the Peking University, China, in 2009, and obtained the M.Eng. degree and the Ph.D. degree at University of Tokyo, in 2011 and 2014, respectively. (Curriculum Vita)
My research interests range across computer vision, machine learning, robotics, and data mining. I have published top-tier journal and conference papers in these four fields, which include topics of deep learning, graph theory, unsupervised learning, object detection, 3D reconstruction, 3D point cloud processing, knowledge mining, and etc.
My current research mainly focuses on two main issues in deep learning, i.e., learning from small data and semanticization of neural networks. I aim to unsupervised or weakly-supervised transform the black-box knowledge representation of neural networks into a hierarchical and semantically interpretable model, and simultaneously achieve small-data learning.