Yuanlu Xu's Homepage

Marching with Humility, Humor and Curiosity.

It's a software engineering truism that code is read more often than it is written. Equally well established is that software spends far more time in maintenance than it does in development. Software that cannot be read and understood cannot be maintained, and software that cannot be maintained is hardly worth having. Always bear in mind that the code you write today will be read by somebody - possibly you - someday in the future. Prepare for that day.

- Scott Meyers, Effective STL

Short Biography

This is Yuanlu Xu, a recruit fighting on research frontline, an engineer promoting world progress, a guardian defending his fetters, a gamer drowning in cyber world.

I am currently a third year Ph.D. candidate at University of California, Los Angeles advised by Prof. Song-Chun Zhu. My research interests are in computer vision and statistical modeling and inference.

I received a BE degree with honors from the School of Software and a MEng degree from School of Information Science and Technology, both in Sun Yat-Sen University.

News

  • I attended AAAI-17 conference and gave a oral presentation for our cross-view people tracking paper. (Feb 2017)
  • I had a AAAI paper accepted, regarding spatio-temporal parsing in cross-view people tracking. (Nov 2016)
  • I passed the oral qualify exam and became a Ph.D. candidate. (Mar 2016)
  • I had a CVPR paper accepted, co-authored with Assoc. Prof. Xiaobai Liu and Prof. Song-Chun Zhu. (Feb 2016)

Research Interest

Computer Vision

  • Spatio-temporal analysis: multi-view video analysis, object identification and tracking, action detection, behavior analysis
  • Spatio-temporal reasoning: occlusion handling, abnormality detection and correction

Statistical Modeling and Inference

  • Deep learning: CNN, RNN, LSTM
  • Graphical models: MRF, CRF, network flow, graph matching
  • Monte Carlo methods: Swensden-Wang Cuts, composite cluster sampling