Jianbo Shi
Assistant Professor, CIS
Research Interests
I work on computer vision, particularly in the area of
1) human recognition: recognizing individual from gait, summarize human
activity in a long video, detecting and tracking people body movement
and gesture; 2) image segmentation and object recognition: developing
general grouping mechanism with spectral graph partitioning,
integration image segmentation with object recognition; 3) building
smart, un-intrusive.
Current Projects
- Human
Recognition: We are developing computer algorithms to recognize
human at multiple levels of abstractions: from the basic body limb
tracking, to human identification, to gesture recognition, to activity
inference.
- Image
Segmentation and Object Recognition: Our research is motivated by
two sets of questions,1) how to extract “interesting” patterns from
data, I believe the grouping mechanism that serves as a general
computational engine in perception, and 2) how to guide the grouping
process to achieve specific vision tasks, such as recognizing familiar
object shapes. In this direction, we have been pursuing a line of
research building upon spectral graph theory.
- Intelligent
Reality: We envision a system with digital projectors as
"actuators", cameras as "sensors", computers as "smart agents". This
system is intended to provide un-intrustive intelligent assistant to
human in a conventional environment. We have developed a "telegraffiti"
device which allows people to communicate remotely use normal pen and
paper.
Representative Publications
- S. Yu and R. Gross and J. Shi. Concurrent Object
Segmentation and Recognition with Graph Partitioning. Neural
Information Processing Systems NIPS 2002. pdf
- H. Zhong and J. Shi. Summarizing Human Activity in
Video. Submitted to IEEE Conf. Computer Vision and Pattern
Recognition CVPR 03.
- J. Gao and J. Shi. Inferring Human Upper Body
Motion. Submitted to IEEE Conf. Computer Vision and Pattern
Recognition CVPR 03. pdf
- R. Collins, R. Gross, J. Shi. Silhouette-based Human
Identification from Body Shape and Gait. 5th International
Conference on Automatic Face and Gesture Recognition, May 2002. pdf
- S. Mahamud , M. Hebert , and J. Shi. Object
Recognition using Boosted Discriminants. IEEE Conference on
Computer Vision and Pattern Recognition (CVPR), Kauai, Hawaii,
December 11-13, 2001. ps
- M. Maila and J. Shi. Learning Segmentation with
Random Walk. Neural Information Processing Systems (NIPS,)
2001. html
- S. Yu and J. Shi. Grouping with Bias. Conference
on Neural Information Processing Systems (NIPS'01), Vancouver, BC,
December 3-5, 2001. pdf
- J. Shi and J. Malik. Normalized Cuts and Image
Segmentation. IEEE Transactions on Pattern Analysis and Machine
Intelligence (PAMI), 2000. html
- J. Shi and J. Malik. Motion Segmentation and
Tracking Using Normalized Cuts. International Conference on
Computer Vision (ICCV), January 1998, Bombay, India. html
- J. Shi and C. Tomasi. Good Features to Track. IEEE
Conference on Computer Vision and Pattern Recognition, June 1994,
pp. 593-600. html
Teaching
|
|
Contact Information
| Office: |
466 Levine/GRW |
| Phone: |
215-746-2851 |
| Email: |
jshi at host cis.upenn.edu |
| Mail: |
Computer and Information Science
University of Pennsylvania
3330 Walnut Street
Philadelphia, PA 19104
|
|
