Learning the Stylistic Similarity Between Human Motions

  • Yu-Ren Chien
  • Jing-Sin Liu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4291)


This paper presents a computational model of stylistic similarity between human motions that is statistically derived from a comprehensive collection of captured, stylistically similar motion pairs. In this model, a set of hypersurfaces learned by single-class SVM and kernel PCA characterize the region occupied by stylistically similar motion pairs in the space of all possible pairs. The proposed model is further applied to a system for adapting an existing clip of human motion to a new environment, where stylistic distortion is avoided by enforcing stylistic similarity of the synthesized motion to the existing motion. The effectiveness of the system has been verified by 18 distinct adaptations, which produced walking, jumping, and running motions that exhibit the intended styles as well as the intended contact configurations.


Human Motion Motion Segment Training Pattern Similarity Judgment Human Activity Recognition 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Witkin, A., Kass, M.: Spacetime constraints. In: SIGGRAPH, pp. 159–168 (1988)Google Scholar
  2. 2.
    Schölkopf, B., Platt, J.C., Shawe-Taylor, J., Smola, A.J., Williamson, R.C.: Estimating the support of a high-dimensional distribution. Neural Computation 13, 1443–1471 (2001)MATHCrossRefGoogle Scholar
  3. 3.
    Schölkopf, B., Smola, A., Müller, K.R.: Nonlinear component analysis as a kernel eigenvalue problem. Neural Computation 10, 1299–1319 (1998)CrossRefGoogle Scholar
  4. 4.
    Liu, C.K., Popović, Z.: Synthesis of complex dynamic character motion from simple animations. In: SIGGRAPH, pp. 408–416 (2002)Google Scholar
  5. 5.
    Grochow, K., Martin, S.L., Hertzmann, A., Popović, Z.: Style-based inverse kinematics. ACM Trans. Graph. 23, 522–531 (2004)CrossRefGoogle Scholar
  6. 6.
    Arikan, O., Forsyth, D.A., O’Brien, J.F.: Motion synthesis from annotations. ACM Transactions on Graphics (TOG) 22, 402–408 (2003)CrossRefMATHGoogle Scholar
  7. 7.
    Ben-Arie, J., Wang, Z., Pandit, P., Rajaram, S.: Human activity recognition using multidimensional indexing. IEEE Trans. Pat. Anal. Mach. Intel. 24, 1091–1104 (2002)CrossRefGoogle Scholar
  8. 8.
    Rao, C., Yilmaz, A., Shah, M.: View-invariant representation and recognition of actions. International Journal of Computer Vision 50, 203–226 (2002)MATHCrossRefGoogle Scholar
  9. 9.
    Gleicher, M.: Motion editing with spacetime constraints. In: Proceedings of the 1997 symposium on Interactive 3D graphics, p. 139 (1997)Google Scholar
  10. 10.
    Gleicher, M.: Retargetting motion to new characters. In: SIGGRAPH, pp. 33–42 (1998)Google Scholar
  11. 11.
    Lee, J., Shin, S.Y.: A hierarchical approach to interactive motion editing for human-like figures. In: SIGGRAPH, pp. 39–48 (1999)Google Scholar
  12. 12.
    Popović, Z., Witkin, A.: Physically based motion transformation. In: SIGGRAPH (1999)Google Scholar
  13. 13.
    Sulejmanpašić, A., Popović, J.: Adaptation of performed ballistic motion. ACM Trans. Graph. 24, 165–179 (2005)CrossRefGoogle Scholar
  14. 14.
    Tak, S., Ko, H.S.: A physically-based motion retargeting filter. ACM Trans. Graph. 24 (2005)Google Scholar
  15. 15.
    Pollard, N.S., Behmaram-Mosavat, F.: Force-based motion editing for locomotion tasks. In: Proceedings of the IEEE International Conference on Robotics and Automation (2000)Google Scholar
  16. 16.
    Pollard, N.S.: Simple machines for scaling human motion. In: Computer Animation and Simulation 1999 (1999)Google Scholar
  17. 17.
    Liu, C.K., Hertzmann, A., Popović, Z.: Learning physics-based motion style with nonlinear inverse optimization. ACM Trans. Graph. 24, 1071–1081 (2005)CrossRefGoogle Scholar
  18. 18.
    Fod, A., Matarić, M.J., Jenkins, O.C.: Automated derivation of primitives for movement classification. Autonomous Robots 12, 39–54 (2002)MATHCrossRefGoogle Scholar
  19. 19.
    Fang, A.C., Pollard, N.S.: Efficient synthesis of physically valid human motion. ACM Transactions on Graphics (TOG) 22, 417–426 (2003)CrossRefGoogle Scholar
  20. 20.
    de Leva, P.: Adjustments to Zatsiorsky-Seluyanov’s segment inertia parameters. J. Biomechanics 29, 1223–1230 (1996)CrossRefGoogle Scholar
  21. 21.
    Schittkowski, K.: Solving constrained nonlinear least squares problems by a general purpose SQP-method. In: Hoffmann, K.H., et al. (eds.) Trends in Math. Optim., pp. 295–309 (1988)Google Scholar
  22. 22.
    Gill, P.E., Murray, W., Saunders, M.A.: SNOPT: An SQP algorithm for large-scale constrained optimization. Technical Report NA–97–2, Dept. Mathematics, UCSD (1997)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Yu-Ren Chien
    • 1
  • Jing-Sin Liu
    • 1
  1. 1.Institute of Information ScienceAcademia SinicaTaiwan

Personalised recommendations