Xiao Lin

Ph.D. Student

Virginia Tech

Email: linxiao (a)

I am a fourth year Ph.D. student in the ECE department at Virginia Tech. I work in the Computer Vision Lab and I am advised by Devi Parikh. My research is in computer vision, especially transfering knowledge between different modalities.

Virginia Tech
2010 - Present
Tsinghua University
2006 - 2010



Leveraging Visual Question Answering for Image-Caption Ranking

Xiao Lin, Devi Parikh

ECCV 2016

"VQA facts => Image captioning"


Learning Common Sense Through Visual Abstraction

Ramakrishna Vedantam, Xiao Lin, Tanmay Batra, Larry Zitnick, Devi Parikh

ICCV 2015

"Visual Abstraction => Common Sense"


Don't Just Listen, Use Your Imagination: 

Leveraging Visual Common Sense for Non-Visual Tasks

Xiao Lin, Devi Parikh

CVPR 2015 (Oral)

"Visual Abstraction => Language"


Combining the Best of Graphical Models and ConvNets for Semantic Segmentation

Michael Cogswell, Xiao Lin, Senthil Purushwalkam, Dhruv Batra

arXiv 2014

"Classification => Segmentation"