Jia Xu, Ph.D.

Research Scientist
Intel Visual Computing Lab

Email: jiaxu [at] cs.wisc.edu
Picture of Jia Xu

Teaching


Teaching Assistant of CS766 Computer Vision, Spring 2015

Teaching Assistant of CS766 Computer Vision, Spring 2014

  • Create and maintain an online classroom on Canvas. Interact and help students with questions on lectures and assignments
  • Introduce a new component to broaden students' sight on modern computer vision advances: students review one paper from the most popular papers (10~15) in recent CVPR/ICCV/ECCV (with one conference set per week)
  • Guide students through class assignments and multi-week final research projects
  • Give a guest lecture on scene classification

Teaching Assistant of BMI/CS 767 Methods in Medical Image Analysis, Spring 2013

  • Create problem sets for the students to learn computational methods and programming
  • Guide students through class assignments and final projects

Outreach


Interactive Demonstration on Temperature and Volume Expansion, UW-Madison Science Expeditions, April 2013

    Together with Dallas Wulf and Matthew Starr, we created an educational tabletop on temperature and volume expansion. Through a combination of a large (and fun!) interactive model of a REAL thermometer, an interactive computer animation of atomic motion in thermometers, and diagrams of thermometers, we teach children and adults "what is a thermometer and how does it work?" and "what is temperature?".

    The tabletop was presented at the 2013 Science Expeditions at Wisconsin Institutes for Discovery.

Interactive Parsing/Segmentation of Large Sets of Images, Wisconsin Science Festival, October 2012

    As part of Singh group consisting of myself and other students, we created a fun, interactive Android application based on our Cosegmentation research, and put it on display at the 2012 Wisconsin Science Festival. The youngsters used their finger to swipe a simple line through a dog shown in one picture on the screen. Our cosegmentation app used this prompt to isolate the entire dog and remove the background across a set of such images. Hundred of children and adults were drawn to the demonstration, which gave them hands-on experience with a tablet that showed how a computer might see pictures as a human does.

    Our research together with this demonstration is featured on UWSMPH News.

 

Computer Sciences | UW Home
Locations of visitors to this page
eXTReMe Tracker