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

Titel:: Robust Multi-Modal Group Action Recognition in Meetings from Disturbed Videos with the Asynchronous Hidden Markov Model
Autor(en):: 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
Kongress- / Buchtitel:: IEEE International Conference on Image Processing, 2007. ICIP 2007
Band / Teilband / Volume:: 2
Jahr:: 2007
Seiten:: 213--216
Volltext / DOI:: doi:10.1109/ICIP.2007.4379130
BibTeX

Vorkommen: