I completed my PhD at the Robotics Institute at Carnegie Mellon University in March 2006. I got my B.E. and M.S. degrees in Electronic Engineering from Tsinghua University, P.R. China, in 1998 and 2001 respectively.

Research

My primary interest is in the intelligence of perception. Specifically, I study computer vision, pattern recognition and machine learning, with an emphasis on statistical methods and their practical applications.

My Ph.D. thesis work involves matching articulated object models to still images. The human body is a typical example of a nonrigid, articulated object. Body localization has a 20-year history in computer vision, yet remains one of the fundamental unsolved problems. I studied three versions of this problem with increasing difficulty:

• Single image w/ background model, walking, side view (CVPR'04)

• Single image w/ background model, walking, arbitrary viewpoint (ICCV'05)

• Single image, arbitrary pose, arbitrary viewpoint (CVPR'06)

Some other problems I have worked on include:

• Offline Chinese handwriting recognition

• Cervical cancer detection in multispectral Pap smear images

• Discriminative subspace induction

Images & Data

• Ground truth labeling of CMU MoBo Dataset. (example movie, 10MB)



• Test images for human body localization.

Selected Publications

• J. Zhang, J. Luo, R. Collins, Y. Liu, Body Localization in Still Images Using Hierarchical Models and Hybrid Search, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2, pp. 1536-1543, 2006. (pdf)

• J. Zhang, R. Collins, Y. Liu, Bayesian Body Localization Using Mixture of Nonlinear Shape Models, IEEE International Conference of Computer Vision (ICCV), vol. 1, pp. 725-732, 2005. (pdf)

• J. Zhang, R. Collins, Y. Liu, Representation and Matching of Articulated Shapes, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), vol.2, pp. 342-349, 2004. (pdf)

• J. Zhang, Y. Liu, SVM Decision Boundary Based Discriminative Subspace Induction, Pattern Recognition, vol. 38, no. 10, pp. 1746-1758, October, 2005. (pdf)

• J. Zhang, Y. Liu, Cervical Cancer Detection Using SVM Based Feature Screening, International Conference on Medical Image Computing and Computer Aided Intervention (MICCAI), vol. 2, pp. 873-880, 2004. (pdf)

• Y. Liu, T. Zhao, J. Zhang, Learning Multispectral Texture Features for Cervical Cancer Detection, IEEE International Symposium on Biomedical Imaging: Macro to Nano (ISBI), pp. 169-172, 2002. (pdf)

• J. Zhang, X. Ding, Multi-Scale Feature Extraction and Nested-Subset Classifier Design for High Accuracy Handwritten Character Recognition, International Conference on Pattern Recognition (ICPR), vol. 2, pp. 581-584, 2000.

Misc

Avi Kak's thoughts on what it takes to produce a good PhD thesis

»ªÒôÂÛ̳ (Chinese folk music forum)

Some "personal" photos