Ji Zhao ()

Post-doctoral Research Associate
The Robotics Institute
School of Computer Science
Carnegie Mellon University

Office: 110 Smith Hall, 5000 Forbes Avenue, Pittsburgh, PA 15213
Phone: 412-268-4315 (office)
Email: zhaoji84 (at) gmail dot com
Curriculum Vitae [
PDF]


Short Biography
I am currently working in the Human Sensing Lab and Component Analysis Lab directed by Prof. Fernando De la Torre. Before that, I received Ph.D degree in 2012 from Huazhong University of Science and Technology.
Research Interests
Generally speaking, my research interests lie in computer vision and machine learning. My current research is focused on image classification and kernel-based learning.
Selected Publications [Full Publications]
Robust Point Matching via Vector Field Consensus.
Jiayi Ma, Ji Zhao, Jinwen Tian, Alan L. Yuille, Zhuowen Tu.
IEEE Transactions on Image Processing, to appear.
Ensemble of Circular Discrepancy for Efficient Two-Sample Test.
Ji Zhao, Deyu Meng.
NIPS Workshop on Randomized Methods for Machine Learning (RMML2013), 2013.
Cyclic Weighted Median Method for L1 Low-Rank Matrix Factorization with Missing Entries. [pdf] [code]
Deyu Meng, Zongben Xu, Lei Zhang, Ji Zhao.
The Twenty-Seventh AAAI Conference on Artificial Intelligence (AAAI-13), 2013.
Robust Estimation of Nonrigid Transformation for Point Set Registration. [pdf] [code link] [poster]
Jiayi Ma, Ji Zhao, Jinwen Tian, Zhuowen Tu, Alan L. Yuille.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013.
Regularized Vector Field Learning with Sparse Approximation for Mismatch Removal. [pdf] [code link]
Jiayi Ma, Ji Zhao, Jinwen Tian, Xiang Bai, Zhuowen Tu.
Pattern Recognition. 46(12):3519 - 3532, 2013.
Mismatch Removal via Coherent Spatial Mapping. [pdf] [code link]
Jiayi Ma, Ji Zhao, Yu Zhou, Jinwen Tian.
International Conference on Image Processing (ICIP), 2012.
A Robust Method for Vector Field Learning with Application to Mismatch Removing. [pdf] [code] [poster]
Ji Zhao, Jiayi Ma, Jinwen Tian, Jie Ma, Dazhi Zhang.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011.
The VFC algorithm was introduced at ICCV 2013 tutorial on Dense Image Correspondences for Computer Vision.

Last update: December 2013