Paper Info
Title
Conversation Scene Analysis with Dynamic Bayesian Network Basedon Visual Head Tracking
Abstract
ABSTRACT A novel method,based on a probabilistic model for con- versation scene analysis is proposed that can infer conversa- tion structure from video sequences of face-to-face commu- nication. Conversation structure represents the type of con- versation such as monologue or dialogue, and can indicate who is talking / listening to whom. This study assumes that the gaze directions of participants provide cues for discerning the conversation structure, and can be identified from head di- rections. For measuring head directions, the proposed method newly employs a visual head tracker based on Sparse-Template Condensation. The conversation model is built on a dynamic Bayesian network and is used to estimate the conversation structure and gaze directions from observed head directions and utterances. Visual tracking is conventionally thought to be less reliable than contact sensors, but experiments confirm that the proposed method achieves almost comparable perfor- mance,in estimating gaze directions and conversation struc- ture to a conventional sensor-based method.
Year
DOI
Venue
2006
10.1109/ICME.2006.262677
Toronto, Ont.
Keywords
Field
DocType
belief networks,image representation,image sensors,image sequences,probabilistic logic,tracking,conversation scene analysis,conversation structure representation,dynamic Bayesian network,face-face communication,gaze direction,head direction,probabilistic model,sparse-template condensation,video sequence,visual head tracking
Computer vision,Conversation,Teleconference,Computer science,Active listening,Speech recognition,Eye tracking,Artificial intelligence,Statistical model,Probabilistic logic,Dynamic Bayesian network,Bayesian probability
Conference
ISBN
Citations 
PageRank 
1-4244-0367-7
26
2.05
References 
Authors
6
4
Name
Order
Citations
PageRank
Kazuhiro Otsuka161954.15
Junji Yamato21120165.72
Yoshinao Takemae314813.42
Hiroshi Murase41927523.30