Xiaochuan Fan Seize the day

About me

Xiaochuan Fan is a PhD candidate in Computer Vision Lab within Computer Science & Engineering Department at University of South Carolina, working with Prof. Song Wang. His research interests are in computer vision and machine learning, especially estimating 2D/3D human poses from images using novel pose representation and deep learning.

Before moving to the University of South Carolina to pursue a Ph.D, Xiaochuan Fan was an algorithm engineer at Thomson (now Technicolor) from 2005 to 2008 and worked as a senior multimedia system engineer at Availink from 2008 to 2012. Xiaochuan Fan received his B.S. in Electronics & Information Technology and M.S. in Signal & Information Processing from Tianjin University in 2002 and 2005, respectively.


Email: fan23@email.sc.edu

3D19 Swearingen Engineering Center
University of South Carolina,
Columbia, SC 29208, USA


3/18 Dissertation Proposal

3/15 One paper accepted as a poster at CVPR 2015

Recent Publications

  • Combining local appearance and holistic view: Dual-source deep neural
    networks for human pose estimation
    Xiaochuan Fan, Kang Zheng, Yuewei Lin, and Song Wang
    CVPR 2015
  • Pose Locality Constrained Representation for 3D Human Pose
    Xiaochuan Fan, Kang Zheng, Youjie Zhou, and Song Wang
    ECCV 2014
  • Co-interest Person Detection from Multiple Wearable Camera Videos
    Yuewei Lin, Kareem Abdelfatah, Youjie Zhou, Xiaochuan Fan,
    Hongkai Yu, Hui Qian, Song Wang
    ICCV, 2015
  • Video-based Action Detection using Multiple Wearable Cameras
    Kang Zheng, Yuewei Lin, Youjie Zhou, Dhaval Salvi, Xiaochuan Fan,
    Dazhou Guo, Zibo Meng, and Song Wang
    ECCV Workshop on ChaLearn Looking at People, 2014

Working Experience

  • Senior Multimedia System Engineer
    2008 - 2012 | Beijing, China

  • Video Algorithm Engineer
    2005 - 2008 | Beijing, China
    Thomson (rebranded as Technicolor since 2010)

Awards and Honors

    Travel Grant Award from CVPR Doctoral Consortium, 2015

    First Place, Poster Awards, Gamecock Computing Symposium, 2014

Free track counters