ML Anthology

Recognition of Temporal Structures: Learning Prior and Propagating Observation Augmented Densities via Hidden Markov States

Shaogang Gong, Michael Walter, Alexandra Psarrou
ICCV 1999 pp. 157-162
doi:10.1109/ICCV.1999.791212 /iccv/1999/gong1999iccv-recognition/

Abstract

An algorithm is described for modelling and recognising temporal structures of visual activities. The method is based on (1) learning prior probabilistic knowledge using hidden Markov models, (2) automatic temporal clustering of hidden Markov states based on expectation maximisation and (3) using observation augmented conditional density distributions to reduce the number of samples required for propagation and therefore improve recognition speed and robustness.

ICCV Semantic Scholar

Cite

Text

Gong et al. "Recognition of Temporal Structures: Learning Prior and Propagating Observation Augmented Densities via Hidden Markov States." IEEE/CVF International Conference on Computer Vision, 1999. doi:10.1109/ICCV.1999.791212

Markdown

[Gong et al. "Recognition of Temporal Structures: Learning Prior and Propagating Observation Augmented Densities via Hidden Markov States." IEEE/CVF International Conference on Computer Vision, 1999.](https://mlanthology.org/iccv/1999/gong1999iccv-recognition/) doi:10.1109/ICCV.1999.791212

BibTeX

@inproceedings{gong1999iccv-recognition,
  title     = {{Recognition of Temporal Structures: Learning Prior and Propagating Observation Augmented Densities via Hidden Markov States}},
  author    = {Gong, Shaogang and Walter, Michael and Psarrou, Alexandra},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {1999},
  pages     = {157-162},
  doi       = {10.1109/ICCV.1999.791212},
  url       = {https://mlanthology.org/iccv/1999/gong1999iccv-recognition/}
}