Active gesture recognition using partially observable Markov decision processes

Proceedings - International Conference on Pattern Recognition

Volumn 3, Issue , 1996, Pages 984-988

  Darrell, Trevor ^a   Pentland, Alex ^a  

^a MIT MEDIA LAB   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

GESTURE RECOGNITION; PATTERN RECOGNITION; VIDEO CAMERAS;

ACTIVE CAMERA; GESTURE RECOGNITION SYSTEM; INTERACTIVE ENVIRONMENTS; PARTIALLY OBSERVABLE MARKOV DECISION PROCESS; Q-LEARNING; SALIENT FEATURES; SPATIAL LOCATION; VISUAL ATTENTION;

REINFORCEMENT LEARNING;

EID: 84898804274     PISSN: 10514651     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICPR.1996.547315     Document Type: Conference Paper

References (17)

1. A. Cassandra, L. P. Kaelbling, and M. Littman. Acting optimally in partially observable stochastic domains. In Proc. AAAI-94, 1994.
2. A. G. Barto, S. J. Bradtke, and S. P. Singh. Real-time learning and control using asynchronous dynamic programming. C.S. T.R. 91-57, U. Mass, 1991.
3. T., Darrell and A., Pentland, Space-Time Gestures. Proceedings IEEE CVPR-93, New York, IEEE Comp. Soc. Press, 1993.
4. T. Darrell, P. Maes, B. Blumberg, and A. P. Pentland, A Novel Environment for Situated Vision and Behavior, Proc. IEEE Workshop for Visual Behaviors, IEEE Comp. Soc. Press, 1994.
5. T. Darrell, I. Essa, and A. P. Pentland, Correlation and Interpolation Networks for Real-time Expression Analysis/Synthesis, In Advances NIPS 7, MIT Press, 1995.
6. T. Darrell and A. Pentland, Attention-driven Expression and Gesture Analysis in an Interactive Environment, in Proc. IWAFGR '95, Zurich, Switzerland, 1995.
7. Darrell, T., Moghaddam, B., and Pentland, A., Active Face Tracking and Pose Estimation in an Interactive Room, to appear Proc. CVPR-96. 1996.
8. T. Jaakkola, S. Singh, and M. Jordan. Reinforcement Learning Algorithm for Partially Observable Markov Decision Problems. In Advances NIPS 7, MIT Press, 1995.
9. T. Poggio and F. Girosi, A Theory of Networks for Approximation and Learning. MIT AI Lab TR-1140, 1989.
10. L. Lin and T. Michell. Reinforcement learning with hidden states. In Proc. AAAI-92, 1992.
11. W. Lovejoy. A survey of algorithmic methods of partially observed markov decision processes. Annals of Operation Reseurch, 28:47-66, 1991.
12. R. A. McCallum. Instance-based State Identification for Reinforcement Learning. In Advances NIPS 7, MIT Press, 1995.
13. E. J. Sondik. The optimal control of partially observable markov processes over the infinite horizon: Discounted costs. Operatzons Reseruch, 26(2):282-304, 1978.
14. R. S. Sutton. Learning to predict by the method of temporal differences. Machine Leurning, 3:9-44, 1988.
15. C. Watkins and P. Dayan. Q-learning. Machine Leurning, 8:279-292, 1992.
16. Whitehead, S., Active perception and reinforcement learning. In Proc. 7th Intl. Conf. ML, June 1990.
17. C. Wren, A. Azarbayejani, T. Darrell, and A. Pentland, Pfinder: Real-Time Tracking of the Human Body, MIT Media Lab Perceptual Computing Group Technical Report No. 353, 1994.