@inproceedings{Black:MIT:2001,
  title = {Learning and tracking cyclic human motion},
  booktitle = {Advances in Neural Information Processing Systems 13, NIPS},
  abstract = {We present methods for learning and tracking human motion in video. We estimate a statistical model of typical activities from a large set of 3D periodic human motion data by segmenting these data automatically into "cycles". Then the mean and the principal components of the cycles are computed using a new algorithm that accounts for missing information and enforces smooth transitions between cycles. The learned temporal model provides a prior probability distribution over human motions that can be used
  in a Bayesian framework for tracking human subjects in complex
  monocular video sequences and recovering their 3D motion.},
  pages = {894-900},
  editors = {Leen, Todd K. and Dietterich, Thomas G. and Tresp, Volker},
  publisher = {The MIT Press},
  year = {2001},
  slug = {black-mit-2001},
  author = {Ormoneit, D. and Sidenbladh, H. and Black, M. J. and Hastie, T.}
}