ML Anthology

Learning the Grammar of Dance

Joshua M. Stuart, Elizabeth Bradley
ICML 1998 pp. 547-555
doi:10.21236/ada452050 /icml/1998/stuart1998icml-learning/

Abstract

Abstract : Human motion sequences that are generated by computer algorithms may contain abrupt transitions: places where consecutive body positions would require physically impossible or stylistically illegal moves. We use graph--theoretic methods to learn the grammar of joint movements in a given corpus and then apply memory-bounded A* search to the resulting transition graphs--using an in order to reduce the search space--to find appropriate interpolation sequences. The application that motivated the development of these methods is an algorithm that uses the mathematical properties of chaos to generate variations on dance and martial arts sequences.

PDF Semantic Scholar

Cite

Text

Stuart and Bradley. "Learning the Grammar of Dance." International Conference on Machine Learning, 1998. doi:10.21236/ada452050

Markdown

[Stuart and Bradley. "Learning the Grammar of Dance." International Conference on Machine Learning, 1998.](https://mlanthology.org/icml/1998/stuart1998icml-learning/) doi:10.21236/ada452050

BibTeX

@inproceedings{stuart1998icml-learning,
  title     = {{Learning the Grammar of Dance}},
  author    = {Stuart, Joshua M. and Bradley, Elizabeth},
  booktitle = {International Conference on Machine Learning},
  year      = {1998},
  pages     = {547-555},
  doi       = {10.21236/ada452050},
  url       = {https://mlanthology.org/icml/1998/stuart1998icml-learning/}
}