Learning kernel-based HMMs for dynamic sequence synthesis

Graphical Models

Volumn 65, Issue 4, 2003, Pages 206-221

  Wang, Tian Shu ^a   Zheng, Nan Ning ^a   Li, Yan ^b   Xu, Ying Qing ^b   Shum, Heung Yung ^b  

^a XI'AN JIAOTONG UNIVERSITY   (China)

^b MICROSOFT RESEARCH ASIA   (China)

Author keywords

Animation; Hidden Markov model; Human motion synthesis; Motion analysis

Indexed keywords

ANIMATION; CONFORMAL MAPPING; DYNAMIC PROGRAMMING; MARKOV PROCESSES; MATHEMATICAL MODELS; MOTION ESTIMATION; PATTERN RECOGNITION; VIRTUAL REALITY;

DYNAMIC SEQUENCE SYNTHESIS; HUMAN MOTION SYNTHESIS; KERNEL BASED HIDDEN MARKOV MODELS; KERNEL BASED STATE DENSITY;

COMPUTER GRAPHICS;

MUSIC;

EID: 0041521139     PISSN: 15240703     EISSN: None     Source Type: Journal    
DOI: 10.1016/S1524-0703(03)00040-7     Document Type: Article

References (18)

1. Y. Bengio, P. Frasconi, Input/output HMMs for sequence processing, IEEE Trans. Neural Network 7 (5) (1996) 1231-1249.
2. M. Brand, Shadow puppetry, in: ICCV99, 1999.
3. M. Brand, Voice puppetry, in: Proc. ACM Siggraph99, 1999, pp. 21-28.
4. M. Brand, A. Hertzmann, Style machines, in: Proc. ACM Siggraph00, 2000, pp. 183-192.
5. M. Brand, N. Oliver, A. Pentland, Coupled Hidden Markov Models for complex action recognition, Technical Report, MIT Media Lab, tR-427, 1996.
6. C. Bregler, M. Covell, M. Slaney, Video rewrite: driving visual speech with audio, in: Proc. ACM Siggraph97, 1997, pp. 353-360.
7. R.O. Duda, P.E. Hart, D.G. Stork, Pattern Classification, second ed., Wiley, New York, 2000.
8. H. Farberman, The Art of Conducting Technique: A New Perspective, Warner Brothers, Miami, 1997.
9. Z. Ghahramani, M. Jordan, Factorial hidden Markov models, Machine Learn. 29 (1997) 245-273.
10. N. Jojic, N. Petrovic, B.J. Frey, T.S. Huang, Transformed hidden Markov models: estimating mixture models of images and inferring spatial transformations in video sequences, in: IEEE Conf. on Comput. Vision Pattern Recognition, 2000.
11. M. Kearns, Y. Mansour, A. Ng, D. Ron, An experimental and theoretical comparison of model selection methods, Machine Learn. 27 (1) (1997) 7-50.
12. J. MacCormick, Probabilistic modelling and stochastic algorithms for visual localisation and tracking, Ph.D. Thesis, Department of Engineer Science, University of Oxford, 2000.
13. D. MacKay, Information theory, inference and learning algorithms, 2002. Available from .
14. K. Pullen, C. Bregler, Life-like animations with motion textures, 2001. Available from .
15. L.R. Rabiner, A tutorial on hidden Markov models and selected applications in speech recognition, Proc. IEEE 77 (2) (1989) 257-286.
16. S. Curinga, F., Lip movement synthesis using time delay neural networks, in: Proc. EUSIPCO96, 1996.
17. V. Pavlovic, J.M. Regh, Impact of dynamic model learning on classification of human motion, in: CVPR00, 2000.
18. A. Wilson, A. Bobick, Parametric hidden Markov models for gesture recognition, IEEE Trans. Pattern Anal. Machine Intell. 21 (9) (1999).