Graphics enhanced version of this site

Jianbo Shi
Adjunct Faculty (Adjunct)

No longer a member of RI.

For more information, see my personal homepage.

Jump to: Research interests | Keywords | Additional Interests and Responsibilities | Labs & Groups | Projects | Publications

I work on computer vision to develop computational algorithms that will allow the computer to see the world as we humans do. I am currently working on a number of problems including human recognition through body motion (HumanID), segmentation and grouping, image/video retrieval and intelligent desktop.

My long-term research interests center around a broader area of machine intelligence. I see the development of a "visual thinking" module is not only a way for computer to understand the environment around us, but also a promising path for achieving higher level cognitive abilities such as machine memory and learning.

artificial intelligence, computer vision, gesture recognition, machine learning, and object recognition

Chair Robotics Institute Seminar
Chair VASC Seminar

• Human Identification at a Distance - We are developing and evaluating human identification technologies as part of the Defense Advanced Research Projects Agency (DARPA) sponsored program in Human Identification at a Distance (HumanID).
• Intelligent Desktop Group - We are developing vision technologies for intelligent desktops.

• Informedia Digital Video Library - Informedia Digital Video Library - Informedia is pioneering new approaches for automated video and audio indexing, navigation, visualization, summarization search, and retrieval and embedding them in systems for use in education, health care, defense intelligence and understanding of human activity.
• Tele-Graffiti - A system that allows two or more users to communicate remotely via hand-drawn sketches.

• Seeing Through Water
  A.A. Efros, V. Isler, J. Shi, and M. Visontai
  Neural >Information Processing Systems (NIPS 17), 2004. [Abstract]
  Download: pdf [571 KB] copyrighted

• Steady-State Feedback Analysis of Tele-Graffiti
  N. Takao, S. Baker, and J. Shi
  Proceedings of the IEEE International Workshop on Projector-Camera Systems, October, 2003. [Abstract]
  Download: pdf [391 KB] copyrighted

• Tele-Graffiti: A Camera-Projector Based Remote Sketching System with Hand-Based User Interface and Automatic Session Summarization
  N. Takao, J. Shi, and S. Baker
  International Journal of Computer Vision, Vol. 53, No. 2, July, 2003, pp. 115 - 133. [Abstract]
  Download: pdf [892 KB] copyrighted

• Inferring Human Upper Body Motion Using Belief Propagation
  J. Gao and J. Shi
  tech. report CMU-RI-TR-03-06, Robotics Institute, Carnegie Mellon University, June, 2003. [Abstract]
  Download: pdf [2908 KB] copyrighted

• Finding (Un)Usual Events in Video
  H. Zhong and J. Shi
  tech. report CMU-RI-TR-03-05, Robotics Institute, Carnegie Mellon University, May, 2003. [Abstract]
  Download: pdf [3695 KB] copyrighted

• Concurrent Object Segmentation and Recognition with Graph Partitioning
  S. Yu, R. Gross, and J. Shi
  Proceedings of Neural Information Processing Systems (NIPS '02), November, 2002. [Abstract]
  Download: pdf [680 KB] copyrighted

• Silhouette-based Human Identification from Body Shape and Gait
  R. Collins, R. Gross, and J. Shi
  Intl' Conference on Face and Gesture, October, 2002, pp. 351-356. [Abstract]
  Download: pdf [287 KB], ps.gz [432 KB] copyrighted

• Tele-Graffiti
  N. Takao, J. Shi, and S. Baker
  tech. report CMU-RI-TR-02-10, Robotics Institute, Carnegie Mellon University, March, 2002. [Abstract]
  Download: pdf [9121 KB], ps.gz [12531 KB] copyrighted

• Object Recognition using Boosted Discriminants
  S. Mahamud, M. Hebert, and J. Shi
  Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR '01), Vol. 1, December, 2001, pp. 551 - 558. [Abstract]
  Download: pdf [167 KB], ps.gz [289 KB] copyrighted

• Quo Vadis Face Recognition?
  R. Gross, J. Shi, and J. Cohn
  Third Workshop on Empirical Evaluation Methods in Computer Vision, December, 2001. [Abstract]
  Download: pdf [534 KB], ps.gz [5411 KB] copyrighted