Xiaolong Wang


Hometown: Guangzhou, China
Carnegie Mellon University

Student Page: http://www.cs.cmu.edu/~xiaolonw/

Research: Xiaolong’s research focuses on exploiting redundancy in visual data to train visual representations. Specifically, he focuses on automatically extracting supervisory signals from RGBD and video data where human labels are hard to come by.  In these domains, his work utilizes the signals from depth and temporal information respectively to design auxiliary tasks to train convolutional neural network based RGB, RGBD and RGBT (RGB+Time) representations. 

Bio: Xiaolong is a third-year PhD student in the Robotics Institute, Carnegie Mellon University, advised by Professor Abhinav Gupta. His research interests are computer vision and machine learning. He holds a M.S. in Computer Science from Sun Yat-sen University and B.E. in Software Engineering from South China Agricultural University.