Audio-visual fused online context analysis toward smart meeting room

Authors:
Peng Dai;Linmi Tao;Guangyou Xu
Affiliations:
Tsinghua National Lab on Information Science & Technology, Tsinghua University, Beijing, China;Tsinghua National Lab on Information Science & Technology, Tsinghua University, Beijing, China;Tsinghua National Lab on Information Science & Technology, Tsinghua University, Beijing, China
Venue:
UIC'07 Proceedings of the 4th international conference on Ubiquitous Intelligence and Computing
Year:
2007

Citing 8
Cited 1

Automatic Analysis of Multimodal Group Actions in Meetings

IEEE Transactions on Pattern Analysis and Machine Intelligence
Automatic detection of interaction groups

ICMI '05 Proceedings of the 7th international conference on Multimodal interfaces
Situated Observation of Human Activity

CVIIE '05 Proceedings of the Computer Vision for Interactive and Intelligent Environment
A survey on context-aware systems

International Journal of Ad Hoc and Ubiquitous Computing
Context as a dynamic construct

Human-Computer Interaction
Modeling individual and group actions in meetings with layered HMMs

IEEE Transactions on Multimedia
Automatic Meeting Segmentation Using Dynamic Bayesian Networks

IEEE Transactions on Multimedia
Dynamic context capture and distributed video arrays for intelligent spaces

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans

Event-driven content management system for smart meeting room

NEW2AN'11/ruSMART'11 Proceedings of the 11th international conference and 4th international conference on Smart spaces and next generation wired/wireless networking

Quantified Score

Hi-index	0.00

Visualization

Abstract

Context-aware systems incorporate multimodal information to analyze contextual information in users' environment and provide various proactive services according to dynamic context. In this paper, a novel online context analysis framework is proposed to support context-aware computing in smart meeting room. A novel dynamic context model is presented to model human group interactions. Robust audio and visual modules are integrated for the effective processing of multimodal signals from various sensors, based on which a multi-level dynamic context reasoning mechanism is adopted for the online understanding of group interactions in meeting scenarios. Experimental results show the effectiveness of our framework.