<?xml version="1.0" encoding="UTF-8"?>
<collection xmlns="http://www.loc.gov/MARC21/slim">
	<record>
		<datafield tag="980" ind1=" " ind2=" ">
			<subfield code="a">CONF</subfield>
		</datafield>
		<datafield tag="970" ind1=" " ind2=" ">
			<subfield code="a">Le_MEDIAEVAL_2016/IDIAP</subfield>
		</datafield>
		<datafield tag="245" ind1=" " ind2=" ">
			<subfield code="a">EUMSSI team at the MediaEval Person Discovery Challenge 2016</subfield>
		</datafield>
		<datafield tag="700" ind1=" " ind2=" ">
			<subfield code="a">Le, Nam</subfield>
		</datafield>
		<datafield tag="700" ind1=" " ind2=" ">
			<subfield code="a">Meignier, Sylvain</subfield>
		</datafield>
		<datafield tag="700" ind1=" " ind2=" ">
			<subfield code="a">Odobez, Jean-Marc</subfield>
		</datafield>
		<datafield tag="653" ind1="1" ind2=" ">
			<subfield code="a">face clustering</subfield>
		</datafield>
		<datafield tag="653" ind1="1" ind2=" ">
			<subfield code="a">OCR</subfield>
		</datafield>
		<datafield tag="653" ind1="1" ind2=" ">
			<subfield code="a">person identification</subfield>
		</datafield>
		<datafield tag="653" ind1="1" ind2=" ">
			<subfield code="a">Speaker Diarization</subfield>
		</datafield>
		<datafield tag="856" ind1="4" ind2="0">
			<subfield code="i">EXTERNAL</subfield>
			<subfield code="u">http://publications.idiap.ch/attachments/papers/2016/Le_MEDIAEVAL_2016.pdf</subfield>
			<subfield code="x">PUBLIC</subfield>
		</datafield>
		<datafield tag="711" ind1="2" ind2=" ">
			<subfield code="a">MediaEval Benchmarking Initiative for Multimedia Evaluation</subfield>
			<subfield code="c">Hilversum, Netherlands</subfield>
		</datafield>
		<datafield tag="260" ind1=" " ind2=" ">
			<subfield code="c">2016</subfield>
		</datafield>
		<datafield tag="520" ind1=" " ind2=" ">
			<subfield code="a">We present the results of the EUMSSI team’s participation in the Multimodal Person Discovery task. The goal is to identify all people who simultaneously appear and speak in a video corpus. In the proposed system, besides improving each modality, we emphasize on the ranking of multiple results from both audio stream and visual stream.</subfield>
		</datafield>
	</record>
</collection>