Title | ||
---|---|---|
A Multi-Modal Graphical Model For Robust Recognition Of Group Actions In Meetings From Disturbed Videos |
Abstract | ||
---|---|---|
In this work we present a novel multi-modal mixed-state dynamic Bayesian network (DBN) for robust meeting event classification from disturbed videos. The model uses information from the audio and the visual channel to structure meetings into segments. Within the DBN a multi-stream hidden Markov model (HMM) is coupled with a linear dynamical system (LDS) to compensate disturbances in the visual channel. Thereby the HMM is used as driving input for the LDS. Thus the model can handle noise and occlusions in the video. Experimental results on real meeting data show that the new model is highly preferable to all single-stream approaches. Compared to a baseline multi-modal early fusion HMM, the new DBN is 3.5%, respectively up to 6.1% better for clear and visual disturbed data, this corresponds to a relative error reduction of 23.6%, respectively 29.9%. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1109/ICIP.2005.1530418 | 2005 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), VOLS 1-5 |
Keywords | Field | DocType |
hidden markov models,relative error,linear dynamical system,image recognition,graphical model,group action,dynamic bayesian network,hidden markov model | Linear dynamical system,Computer science,Artificial intelligence,Computer vision,Variable-order Bayesian network,Pattern recognition,Markov model,Communication channel,Speech recognition,Graphical model,Hidden Markov model,Approximation error,Dynamic Bayesian network | Conference |
ISSN | Citations | PageRank |
1522-4880 | 5 | 0.52 |
References | Authors | |
1 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Marc Al-Hames | 1 | 116 | 8.75 |
Gerhard Rigoll | 2 | 2788 | 268.87 |