William Bokui Shen 沈博魁

bshen88 at stanford.edu [Github] [Google Scholar]

About me

I am starting my Ph.D. at Stanford University's Computer Science Department in September. I am currently an undergraduate senior at Stanford. I am supervised by Silvio Savarese in SVL (formerly CVGL). I also had the luck to collborate with Leo Guibas, Jitendra Malik and Juan Carlos Niebles on various projects. My research interests lie in Computer Vision (generic perception in particular) and robotics learning.

News:

  • 2018.03 Received Frederick Emmons Terman Engineering Scholastic Award (Top 5% of entire Stanford Engineering School)

  • 2018.02 Paper accepted as Oral at CVPR2018 (Taskonomy: Disentangling Task Transfer Learning) [website]

  • 2018.02 Admitted to Stanford University CS Ph.D.!

Education

Sep. 2014 - Present, Department of Computer Science, Stanford University,

Undergraduate Student. GPA: 4.00/4.00

Research with Prof. Silvio Savarese

Internship

Jun. 2016 - Sep. 2016, Project Fi, Google Inc.,

Real time phone call transcription service

Mentor: Madhu R. Adupala

Aug. 2016 - Sep. 2016, Google Brain, Google Inc.,

Measuring Gradient Descend Batch Variance

Mentor: Alex Davies

Honors and Awards

  • Frederick Emmons Terman Engineering Scholastic Award : top 5% of entire engineering graduating class
  • Stanford University Computer Science Department Honor (on-going): undergraduate honor thesis under advisory of Prof. Silvio Savarese and Prof. Leo Guibas.
  • Stanford Tau Beta Pi Engineering Society
  • Stanford CS106A Graphics Contest Champion (Prof. Mehran Sahami, Autumn 2014)

Publications

  • Amir R. Zamir, Alexander Sax*, William B. Shen*, Leonidas Guibas, Jitendra Malik, Silvio Savarese. Taskonomy: Disentangling Task Transfer Learning. [project] [code]
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Oral 2018

    Research on how to learn a set of tasks under optimized total supervision. A broad and comprehensive empirical study of task affinity. A diverse bank of pretrained deep neural networks for 25 different computer vision tasks.

  • Kuo-Hao Zeng, William B. Shen, De-An Huang, Min Sun, Juan Carlos Niebles. Visual Forecasting by Imitating Dynamics in Natural Sequences. [arxiv]
    IEEE International Conference on Computer Vision (ICCV), 2017.

    Research on a general framework for visual forecasting, which directly imitates visual sequences by formulating visual forecasting as an inverse reinforcement learning (IRL) problem.

  • Amir R. Zamir*, Te-lin Wu*, Lin Sun, William B. Shen, Jitendra Malik, Silvio Savarese. Feedback networks. [project] [code]
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017

    Research on novel feedback network paradigm that offers advantages including early prediction, taxonomic compliance and curriculum-based learning over traditional feedforward counterpart.

(*Equally contributed to the project and alphabetically listed)

Services

  • Reviewer for CVPR 2018

Projects

  • CS231A Course Project: William B. Shen, Song Han, Zuozhen Liu. Drone Human Tracking Using Faster RCNN and KCF. [report]

    Course project on implementing Faster-RCNN to detect human and KCF to track human on drones. Heavy optimization with frame-rate using TX1/TK1.

  • Stanford CS106A Graphics Contest Winner (Prof. Mehran Sahami, Autumn 2014)

    Probably the nerdest thing I have done...
    A weird mash-up of Mario, Galagal, Pacman, Star War, RPG.

Photography

    Favorite