<?xml version="1.0" standalone="yes"?>
<Paper uid="C02-1098">
  <Title>Annotation-Based Multimedia Summarization and Translation</Title>
  <Section position="5" start_page="0" end_page="0" type="concl">
    <SectionTitle>
4 Concluding Remarks
</SectionTitle>
    <Paragraph position="0"> We have developed a tool to create multimedia annotation data and a mechanism to applysuchdatatomultimediasummarizationand null translation. The main component of the annotationtoolisamultilingualvoicetranscriptorto null generate transcriptsfrommultilingualspeechin videoclips. Thetoolalsoextractssceneandobject information semi-automatically, describes the data in XML format, and associates the data with content.</Paragraph>
    <Paragraph position="1"> We also presented some advanced applications on multimedia content based on annotation. We have implemented video-to-document transformationthatgeneratesinteractive multi-modal documents, video summarization using a text summarization technique, and video translation. null Linguistic processing is an essential task in those applications so that natural language technologies are still very important in processing multimedia content.</Paragraph>
    <Paragraph position="2"> Ourfuturework includesa more efficient and flexible retrieval of multimedia content for requests in spoken and written natural language.</Paragraph>
    <Paragraph position="3"> Theretrievalofspokendocumentshasalsobeen evaluated in a subtask &amp;quot;SDR (Spoken Document Retrieval) track&amp;quot; at TREC (Text REtrieval Conference) (TREC, 2002). Johnson (Johnson, 2001) suggested from his group's experience on TREC-9 that new challenges such as use of non-lexical information derived directlyfromtheaudioandintegrationwithvideo null data are significant works for the improvement of retrieval performance and usefulness. We, therefore, believe that our research has significant impacts and potetials on the content technology. null</Paragraph>
  </Section>
class="xml-element"></Paper>