@inproceedings{4675,
  title = {Discriminative Subsequence Mining for Action Classification},
  journal = {Proceedings of the 11th IEEE International Conference on Computer Vision (ICCV 2007)},
  booktitle = {ICCV 2007},
  abstract = {Recent approaches to action classification in videos have
  used sparse spatio-temporal words encoding local appearance
  around interesting movements. Most of these approaches
  use a histogram representation, discarding the
  temporal order among features. But this ordering information
  can contain important information about the action
  itself, e.g. consider the sport disciplines of hurdle race
  and long jump, where the global temporal order of motions
  (running, jumping) is important to discriminate between
  the two. In this work we propose to use a sequential
  representation which retains this temporal order. Further,
  we introduce Discriminative Subsequence Mining to find
  optimal discriminative subsequence patterns. In combination
  with the LPBoost classifier, this amounts to simultaneously
  learning a classification function and performing feature
  selection in the space of all possible feature sequences.
  The resulting classifier linearly combines a small number
  of interpretable decision functions, each checking for the
  presence of a single discriminative pattern. The classifier is
  benchmarked on the KTH action classification data set and
  outperforms the best known results in the literature.},
  pages = {1919-1923},
  publisher = {IEEE Computer Society},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  address = {Los Alamitos, CA, USA},
  month = oct,
  year = {2007},
  slug = {4675},
  author = {Nowozin, S. and BakIr, G. and Tsuda, K.},
  month_numeric = {10}
}