web metrics
Yuandong Tian
PhD in Robotics
The Robotics Institute
School of Computer Science
Carnegie Mellon University
Email: yuandong [at] andrew [dot] cmu [dot] edu


Brief Bio

I was born in Shanghai, a beautiful and fast-developing city in China. I studied in Computer Science and Engineering Department, Shanghai Jiao Tong University and graduated as a Bachelor in 2005 and a Master in 2008. I am now a Ph.D candidate in the Robotics Institute, Carnegie Mellon University, working with my advisor Srinivasa Narasimhan.

Now I am working in Google [x] (Self-driving car). See here for my resume.

I received Microsoft Research PhD Fellowship (2011-2013).

Research Direction

In general, I am interested in computer vision and machine learning. In particular, I am working on modeling and understanding non-rigid image deformation and data-driven optimization. My approach can be used for dense image alignment, nonrigid object tracking, human pose estimation, distortion correction, etc. In addition, I am also working on data mining algorithms for crowdsourcing.

Research Projects in CMU

Hierarchical Data-Driven Descent for Efficient Optimal Deformation Estimation[PDF][Detailed Proofs]
Yuandong Tian, Srinivasa G. Narasimhan,
Accepted as Oral in ICCV 2013
Exploring the Spatial Hierarchy of Mixture Models for Human Pose Estimation [PDF]
Yuandong Tian, C. Lawrence Zitnick, Srinivasa G. Narasimhan,
Accepted as Poster in ECCV 2012
Learning from Crowds in the Presence of Schools of Thought [PDF][Dataset][Code][Presentation]
Yuandong Tian, Jun Zhu,
ACM SIGKDD 2012
Depth from Optical Turbulence
Yuandong Tian, Srinivasa G. Narasimhan, Alan J. Vannevel
Accepted as Poster in CVPR 2012
Globally Optimal Estimation of Nonrigid Image Distortion[PDF]
Yuandong Tian, Srinivasa G. Narasimhan,
International Journal of Computer Vision (IJCV), As an extended version of [Tian and Narasimhan, CVPR 2010].
Rectification and 3D reconstruction of Curved Document Images
Yuandong Tian, Srinivasa G. Narasimhan,
Accepted as Oral in CVPR 2011
Local Isomorphism to Solve the Pre-image Problem in Kernel Methods
Dong Huang, Yuandong Tian, Fernando De la Torre
Accepted as Poster in CVPR 2011
A Globally Optimal Data-Driven Approach for Image Distortion Estimation
Yuandong Tian, Srinivasa G. Narasimhan,
Accepted as Oral in CVPR 2010
Seeing through water: Image restoration using model-based tracking
Yuandong Tian, Srinivasa G. Narasimhan,
Accepted as Poster in ICCV 2009
(De) Focusing on Global Light Transport for Active Scene Recovery
Mohit Gupta, Yuandong Tian, Srinivasa G. Narasimhan, Li Zhang
Accepted as Oral in CVPR 2009 [PDF]



Relationship between projector defocus and global illumination for statistically-modeled scenes.
Yuandong Tian, Mohit Gupta, Srinivasa G. Narasimhan, Li Zhang
Technical Report CMU-RI-TR-09-10, Carnegie Mellon University, March 2009.

Previous Research Projects

Easytoon: an easy and quick tool to personalize a cartoon storyboard using family photo album
Shifeng Chen, Yuandong Tian, Fang Wen, Ying-Qing Xu, Xiaoou Tang
ACMMM 2008 [PDF]
A Face Annotation Framework with Partial Clustering and Interactive Labeling
Yuandong Tian, Wei Liu, Rong Xiao, Fang Wen, Xiaoou Tang
Accepted as Poster in CVPR 2007 [PDF]

Notes

Short Notes on Graphcut and MRF
Yuandong Tian, 2009
[PDF]
A short introduction to Riemann Geometry
Yuandong Tian, 2009
[PDF]
Some notes in Pattern Recognition and Machine Learning
Yuandong Tian, 2008
[PDF]

Personal

Poems and Novels

Homebrew programming on Sony PSP (Playstation Portable)