<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-2097">
  <Title>Visual Information Based on Hidden Markov Models</Title>
  <Section position="8" start_page="760" end_page="761" type="concl">
    <SectionTitle>
6 Conclusions
</SectionTitle>
    <Paragraph position="0"> This paper has described an unsupervised topic identification method integrating linguistic and visual information based on Hidden Markov Mod- null els. Our experiments on the two kinds of cooking TV programs showed the effectiveness of integration of linguistic and visual information and incorporation of domain-independent discourse features to domain-dependent features (case frame and background image).</Paragraph>
    <Paragraph position="1"> We are planning to perform object recognition using the automatically-constructed object model and utilize the object recognition results as a feature for HMM-based topic identification.</Paragraph>
  </Section>
class="xml-element"></Paper>