nips nips2006 nips2006-134 nips2006-134-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Graham W. Taylor, Geoffrey E. Hinton, Sam T. Roweis
Abstract: We propose a non-linear generative model for human motion data that uses an undirected model with binary latent variables and real-valued “visible” variables that represent joint angles. The latent and visible variables at each time step receive directed connections from the visible variables at the last few time-steps. Such an architecture makes on-line inference efficient and allows us to use a simple approximate learning procedure. After training, the model finds a single set of parameters that simultaneously capture several different kinds of motion. We demonstrate the power of our approach by synthesizing various motion sequences and by performing on-line filling in of data lost during motion capture. Website: http://www.cs.toronto.edu/∼gwtaylor/publications/nips2006mhmublv/
[1] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, vol. 86, pp. 2278–2324, November 1998.
[2] C. K. Liu, A. Hertzmann, and Z. Popovic, “Learning physics-based motion style with nonlinear inverse optimization,” ACM Trans. Graph., vol. 24, no. 3, pp. 1071–1081, 2005.
[3] O. Arikan, D. A. Forsyth, and J. F. O’Brien, “Motion synthesis from annotations,” in Proc. SIGGRAPH, 2002.
[4] M. Brand and A. Hertzmann, “Style machines.,” in Proc. SIGGRAPH, pp. 183–192, 2000.
[5] Y. Li, T. Wang, and H.-Y. Shum, “Motion texture: a two-level statistical model for character motion synthesis,” in Proc. SIGGRAPH, pp. 465–472, 2002.
[6] R. Urtasun, P. Glardon, R. Boulic, D. Thalmann, and P. Fua, “Style-based Motion Synthesis,” Computer Graphics Forum, vol. 23, no. 4, pp. 1–14, 2004.
[7] M. Welling, M. Rosen-Zvi, and G. E. Hinton, “Exponential family harmoniums with an application to information retrieval.,” in Proc. NIPS 17, 2005.
[8] Y. Freund and D. Haussler, “Unsupervised learning of distributions of binary vectors using 2-layer networks,” in Proc. NIPS 4, 1992.
[9] G. E. Hinton, “Training products of experts by minimizing contrastive divergence.,” Neural Comput, vol. 14, pp. 1771–1800, Aug 2002.
[10] I. Sutskever and G. E. Hinton, “Learning multilevel distributed representations for high-dimensional sequences,” Tech. Rep. UTML TR 2006-003, University of Toronto, 2006.
[11] Y. W. Teh and G. E. Hinton, “Rate-coded restricted Boltzmann machines for face recognition,” in Proc. NIPS 13, 2001.
[12] E. Hsu, K. Pulli, and J. Popoviˆ , “Style translation for human motion,” ACM Trans. Graph., vol. 24, no. 3, c pp. 1082–1089, 2005.
[13] F. S. Grassia, “Practical parameterization of rotations using the exponential map,” J. Graph. Tools, vol. 3, no. 3, pp. 29–48, 1998.
[14] G. E. Hinton, S. Osindero, and Y.-W. Teh, “A fast learning algorithm for deep belief nets,” Neural Comp., vol. 18, no. 7, pp. 1527–1554, 2006.