000083161 001__ 83161
000083161 005__ 20180317093239.0
000083161 037__ $$aREP_WORK
000083161 245__ $$aTracking People in Meetings with Particles
000083161 269__ $$a2004
000083161 260__ $$aMartigny, Switzerland$$bIDIAP$$c2004
000083161 336__ $$aReports
000083161 500__ $$ain Proc. Int. Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS), invited paper, Montreux, Apr. 2005.
000083161 520__ $$aAutomatic meeting analysis is an emerging research field. In this paper, we present stochastic algorithms for tracking people in multi-sensor meeting rooms, for a number of relevant tasks, including tracking multiple people, tracking head pose towards analysis of visual focus-of-attention, and tracking speaker activity using audio-visual information. A Bayesian framework based on Sequential Monte Carlo methods is used in all cases. We discuss the advantages and limitations of our approach, illustrate it with results, and highlight a number of open issues.
000083161 6531_ $$aspeech
000083161 6531_ $$avision
000083161 700__ $$0241066$$aGatica-Perez, Daniel$$g171600
000083161 700__ $$0243995$$aOdobez, Jean-Marc$$g161663
000083161 700__ $$0243960$$aBa, Silèye O.$$g165435
000083161 700__ $$aSmith, Kevin C.
000083161 700__ $$0241533$$aLathoud, Guillaume$$g158806
000083161 8564_ $$uhttp://publications.idiap.ch/downloads/reports/2004/rr-04-71.pdf$$zURL
000083161 8564_ $$s327233$$uhttps://infoscience.epfl.ch/record/83161/files/rr-04-71.pdf$$zn/a
000083161 909CO $$ooai:infoscience.tind.io:83161$$preport$$pSTI
000083161 909C0 $$0252189$$pLIDIAP$$xU10381
000083161 937__ $$aEPFL-REPORT-83161
000083161 970__ $$agatica05b/LIDIAP
000083161 973__ $$aEPFL$$sPUBLISHED
000083161 980__ $$aREPORT