Robust Multi-Modal Group Action Recognition in Meetings from Disturbed Videos with the Asynchronous Hidden Markov Model

Title:: Robust Multi-Modal Group Action Recognition in Meetings from Disturbed Videos with the Asynchronous Hidden Markov Model
Author(s):: Al-Hames, M.; Lenz, C.; Reiter, S.; Schenk, J.; Wallhoff, F.; Rigoll, G.
Abstract:: The asynchronous hidden Markov model (AHMM) models the joint likelihood of two observation sequences, even if the streams are not synchronised. We explain this concept and how the model is trained by the EM algorithm. We then show how the AHMM can be applied to the analysis of group action events in meetings from both clear and disturbed data. The AHMM outperforms an early fusion HMM by 5.7
Book / Congress title:: IEEE International Conference on Image Processing, 2007. ICIP 2007
Volume:: 2
Year:: 2007
Pages:: 213--216
Fulltext / DOI:: doi:10.1109/ICIP.2007.4379130
BibTeX

Occurrences: