Hierarchical multi-channel hidden semi Markov graphical models for activity recognition

  title={Hierarchical multi-channel hidden semi Markov graphical models for activity recognition},
  author={Pradeep Natarajan and Ramakant Nevatia},
  journal={Computer Vision and Image Understanding},
Recognizing human actions from a stream of unsegmented sensory observations is important for a number of applications such as surveillance and human-computer interaction. A wide range of graphical models have been proposed for these tasks, and are typically extensions of the generative hidden Markov models (HMM) or their discriminative counterpart, conditional random fields (CRF). These extensions typically address one of three key limitations in the basic HMM/CRF formalism unrealistic models… CONTINUE READING


Publications referenced by this paper.
Showing 1-10 of 37 references

Tutorial on variational approximation methods

  • T. S. Jaakkola
  • in: In Advanced Mean Field Methods: Theory and…
  • 2000
Highly Influential
3 Excerpts


  • M. Ryoo
  • Aggarwal, Stochastic representation and…
  • 2011
1 Excerpt

Similar Papers

Loading similar papers…