Principal Scientist
Visual Computing and User Interfaces
Contact
I am a Principal Scientist in Nokia Research Center at Palo Alto. I am a member of the Visual Computing and User Interfaces (VCUI) team. My research interests include creating new mobile multimedia technology and user interaction designs, to provide higher quality and style for Nokia mobile phone users.
Prior to joining Nokia, I worked in the School of Computer Science, Carnegie Mellon University for six years. I was a research faculty before leaving, and my research activities were primarily in the areas of computer vision and robotics, with special focus on understanding an environment of human, including activities, faces and written symbols. Some of my previous projects include:
HumanID and Caremedia projects. We developed a system for activity analysis from video cameras in a nursing home, based on robust motion features and a hidden Markov model. The focus is on event understanding and knowledge mining from video.
Interpretation of written symbols.Developed a fully automatic, real time system for detection, recognition, and translation of text /signs from a natural environment. I am also interested in natural language processing (NLP) and machine translation through this work. Some part of this work was performed in the Human Computer Interaction Institute, CMU.
Face expression analysis. My work is focused on generic 3D face modeling from video and rigid head motion stabilization for face expression analysis.
I received my PhD on signal processing, operational research, and control engineering.
Alexander G. Hauptmann, Jiang Gao, R. Yan, Y. Qi, J. Yang, and H.D. Wactlar. Automated Analysis of Nursing Home Observations. IEEE Pervasive Computing, Special Issue on Pervasive Computing for Successful Aging, Vol. 3, No. 2, pp. 15-21, 2004.
Jiang Gao, Robert T. Collins, A.G. Hauptmann and H.D. Wactlar, Articulated Motion Modeling for Activity Analysis. IEEE CVPR’04 Workshop on Articulated and Nonrigid Motion (ANM2004), 2004.
Jiang Gao and Jianbo Shi, Multiple Frame Motion Inference Using Belief Propagation. International Conference on Automatic Face and Gesture Recognition, 2004.
J. F. Cohn, T. Kanade, T. Moriyama, Z. Ambadar, J. Xiao, Jiang Gao, and H. Imanura, A Comparative Study of Alternative FACS Coding Algorithm. Technical Report CMU-RI-TR-02-06, Robotics Institute, Carnegie Mellon University, November, 2001.
Jiang Gao and Jie Yang, An Adaptive Algorithm for Text Detection from Natural Scenes. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’01), Hawaii, 2001.
Jiang Gao, X. Ding and Jing Zheng, Image Pattern Recognition Based on Examples -- A Combined Statistical and Structural-Syntactic Approach. IAPR Joint Workshops on Statistical, Structural and Syntactical Pattern Recognition (S+SSPR'2000), Alicante, Spain, Sept. 2000.
Jiang Gao, Baosheng Hu and Guanzhong Dai, Frequency-Domain Properties of Innovations Sequence and Their Applications. Proc. 14th World Congress of International Federation of Automatic Control (IFAC’99), July, 1999, Beijing.
and more...
Thoughts and Strategies in Information "Mining" from Image/Video. Columbia University, New York, 2003.
Layer Adaptation with Applications to Computer Vision Problems. Microsoft Research, Redmond, 2003.
Motion Segmentation using Optical Flow and Layer Adaptation. CMU Caremedia Project, 2003.
