Research

In high school, I was obsessed with geometry and did a full survey on generalized Fermat problem in Lp space. I rewrote into a formal paper in my undergrad year and further studied its related NP-Hard Euclidean Steiner Tree problem.

Later, I was interested in computer vision and machine learning. I did a facade-based unban scene analysis advised by Prof. Yanxi Liu in Lab of Perception, Action and Cognition. I also explored sparse representation framework on several vision applications advised by Prof. Constantino Lagoa. I had a great time working with Prof. Simon Lucey in The Robotics Institute at Carnegie Mellon University in summer 2016. I also contributed to a medical AI project on lung cancer detection in Tencent YouTu Lab in summer 2017.

Publication

  • End-to-End Multi-task Learning with Attention
    ArXiv Preprint
    Shikun Liu, Edward Johns, and Andrew J. Davison
    [arxiv]
  • Learning a Hierarchical Latent-Variable Model of 3D Shapes
    International Conference on 3D Vision (3DV), 2018 [Oral]
    Shikun Liu, C. Lee Giles, and Alexander G. Ororbia II.
    [paper] [supplementary] [arxiv] [code] [project page]