<?xml version="1.0" encoding="UTF-8"?>
<collection xmlns="http://www.loc.gov/MARC21/slim">
	<record>
		<datafield tag="980" ind1=" " ind2=" ">
			<subfield code="a">REPORT</subfield>
		</datafield>
		<datafield tag="970" ind1=" " ind2=" ">
			<subfield code="a">Korchagin_Idiap-RR-10-2011/IDIAP</subfield>
		</datafield>
		<datafield tag="245" ind1=" " ind2=" ">
			<subfield code="a">Just-in-Time Multimodal Association and Fusion from Home Entertainment</subfield>
		</datafield>
		<datafield tag="700" ind1=" " ind2=" ">
			<subfield code="a">Korchagin, Danil</subfield>
		</datafield>
		<datafield tag="700" ind1=" " ind2=" ">
			<subfield code="a">Motlicek, Petr</subfield>
		</datafield>
		<datafield tag="700" ind1=" " ind2=" ">
			<subfield code="a">Duffner, Stefan</subfield>
		</datafield>
		<datafield tag="700" ind1=" " ind2=" ">
			<subfield code="a">Bourlard, Hervé</subfield>
		</datafield>
		<datafield tag="653" ind1="1" ind2=" ">
			<subfield code="a">association rules</subfield>
		</datafield>
		<datafield tag="653" ind1="1" ind2=" ">
			<subfield code="a">data analysis</subfield>
		</datafield>
		<datafield tag="653" ind1="1" ind2=" ">
			<subfield code="a">multimodal signal processing</subfield>
		</datafield>
		<datafield tag="653" ind1="1" ind2=" ">
			<subfield code="a">sensor fusion</subfield>
		</datafield>
		<datafield tag="856" ind1="4" ind2="0">
			<subfield code="i">EXTERNAL</subfield>
			<subfield code="u">http://publications.idiap.ch/attachments/reports/2011/Korchagin_Idiap-RR-10-2011.pdf</subfield>
			<subfield code="x">PUBLIC</subfield>
		</datafield>
		<datafield tag="088" ind1=" " ind2=" ">
			<subfield code="a">Idiap-RR-10-2011</subfield>
		</datafield>
		<datafield tag="260" ind1=" " ind2=" ">
			<subfield code="c">2011</subfield>
			<subfield code="b">Idiap</subfield>
			<subfield code="a">Martigny, Switzerland</subfield>
		</datafield>
		<datafield tag="771" ind1="2" ind2=" ">
			<subfield code="d">May 2011</subfield>
		</datafield>
		<datafield tag="520" ind1=" " ind2=" ">
			<subfield code="a">In this paper, we describe a real-time multimodal analysis system with just-in-time multimodal association and fusion for a living room environment, where multiple people may enter, interact and leave the observable world with no constraints. It comprises detection and tracking of up to 4 faces, detection and localisation of verbal and paralinguistic events, their association and fusion. The system is designed to be used in open, unconstrained environments like in next generation video conferencing systems that automatically “orchestrate” the transmitted video streams to improve the overall experience of interaction between spatially separated families and friends. Performance levels achieved to date on hand-labelled dataset have shown sufficient reliability at the same time as fulfilling real-time processing requirements.</subfield>
		</datafield>
	</record>
</collection>