Yushi Jing (Kevin Jing)

Computational Perception Lab, GVU
College of Computing
Georgia Institute of Technology
Atlanta, GA 30332
Email: kevin . jing @ gmail . com

I have been working full-time at Google Research since 2006. My research interest include machine learning, computer vision and social networks. My advisor is James M. Rehg. I am also co-advised by Michele Covell and Shumeet Baluja from Google Research.



Past Projects covered by news media

VisualRank, Applying PageRank to Google image search. (Collaboration with Shumeet Baluja). (@Google)
       Article by New York Times, April 28, 2008

Combat Child Porn -- Supply image processing technology to NCMEC (National Center for Missing and Exploited Children) to fight child pornography (Collaboration with Shumeet Baluja and Michele Covell) @Google
       Article by BBC, CBS, April 14th, 2008.
       A video clip from ABC news

Porn Filter for image search engine. (Collaboration with Henry Rowley and Shumeet Baluja) @Google
       Efforts cited by Scientific American , May 2006

Word-of-Mouth (social network) advertising. @Icosystem
       Technology cited in Economist Nov 2006.

Journals

Y. Jing, V. Pavlovic, J. Rehg.  Boosted Bayesian Network Classifier
Accepted for publication at Machine Learning Journal, 2008

Y.jing, S. Baluja.   VisualRank
Accepted for publication at Pattern Analysis and Machine Intelligence, 2008.

Conferences

Y. Jing, S. Baluja,   Apply PageRank to Image Search. to appear in Proc. International World Wide Web Conference (WWW), Beijing, April 2008.

S. Baluja, D. Siva, R. Seth, Y. Jing, J. Yagnik, D. Ravichandran, M. Aly Video Suggestion and Discovery for YouTube: Taking Random Walks Through the View Graph - to appear in Proc. International World Wide Web Conference (WWW), Beijing, April 2008.

Y. Jing, V. Pavlovic, J. Rehg. Efficient discriminative learning of Bayesian network classifiers via Boosted Augmented Naive Bayes - Proceedings of International Conference on Machine Learning (ICML 2005) [ICML Distinguished Student Paper]

H. Rowley, Y. Jing, S. Baluja.  Large Scale Image-Based Adult-Content Filtering - Proceedings of International Conference on Computer Vision Theory and Applications (2006)

Y. Jing, S. Baluja, H. Rowley, Canonical Image Selection from the Web- International Conference on Image and Video Retrieval, 2007

Work Experience

Software Engineer, Google Research, Mountain View, CA

-- Software engineering and research in the field of computer vision and machine learning. Dozen of patents pending.

Analyst, Dentsu (Japan) & Icosystem

-- Software engineering and quantitative analysis of word-of-mouth advertising.

Intern, United Nation (Bonn, Germany)


Education

--B.S., M.S., Ph.D. candidate, in Computer Science, Georgia Tech.
--M.S. candidate in International Affairs, Georgia Tech.
--Trilingual, spent significant time living in China(12+), U.S(12+). and Japan(3+).