Login / Signup

Audio/visual mapping with cross-modal hidden Markov models.

Shengli FuRicardo Gutierrez-OsunaAnna EspositoPraveen K. KakumanuOscar N. Garcia
Published in: IEEE Trans. Multim. (2005)
Keyphrases
  • hidden markov models
  • audio visual
  • cross modal
  • multi modal
  • visual data
  • speech recognition
  • visual information
  • high dimensional
  • image annotation
  • em algorithm