<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>
<head>
</head>
<body bgcolor="#ffffff" text="#000000">
<pre wrap=""> Call for Papers
The 2nd International Workshop on Language Resources for
Content-based Image Retrieval (OntoImage 2008)</pre>
<pre wrap=""></pre>
<pre wrap=""> Held in conjunction with LREC 2008
Marrakech, Morocco
afternoon of May 26, 2008
</pre>
<p class="MsoNormal"><b style=""><span style="" lang="EN-GB">Scope <o:p></o:p></span></b></p>
<p class="MsoNormal"><b style=""><span style="" lang="EN-GB"><o:p> </o:p></span></b></p>
<p class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB">There are two computer-aided methods for
accessing images: <o:p></o:p></span></p>
<ul style="margin-top: 0cm;" type="disc">
<li class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB">indexing textual descriptions (done mostly by public
retrieval engines) <o:p></o:p></span></li>
<ul style="margin-top: 0cm;" type="circle">
<li class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB">assigned manually on community sharing sites, e.g.
Flickr; <o:p></o:p></span></li>
<li class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB">extracted from the text of the web page associated with
the image , e.g. Google<o:p></o:p></span></li>
<li class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB">extracting textual information inside the image using OCR
techniques <o:p></o:p></span></li>
</ul>
<li class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB">indexing low-level visual features (colour, texture,
etc.) of the images (called Content Based Image Retrieval - CBIR).<span
style=""> </span><o:p></o:p></span></li>
</ul>
<p class="MsoNormal" style="margin-left: 18pt; text-align: justify;"><span
style="" lang="EN-GB"><o:p> </o:p></span></p>
<p class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB">Combining these two methods is currently a hot
topic since it involves developing hybrid approaches using automatic
image
tagging from text along with low level visual features from an image to
produce
text metadata. One of the main limitations within state-of-the-art CBIR
resides
in the mismatch (the “Semantic Gap” in image analysis) between
low-level visual
descriptors and the human-understood semantics of picture similarity.
There are
problems of vocabulary at all levels in the description of an image.
There is a
mismatch between the text found around an image, between the keywords
that
people assign to an image, and between the objects that can be
recognized in an
image.<span style=""> </span>How can available language
resources (terminology, thesauri, ontologies, etc.) help? How much must
they be
altered to reduce the semantic gap?<span style=""> </span><o:p></o:p></span></p>
<p class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB"><o:p> </o:p></span></p>
<p class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB">This half-day workshop will present up to 9
papers examining the intersection of language resources and image
analysis and
retrieval. <o:p></o:p></span></p>
<p class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB"><o:p> </o:p></span></p>
<p class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB">We welcome submissions addressing the following
questions:<o:p></o:p></span></p>
<ul style="margin-top: 0cm;" type="disc">
<li class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB">What elements in a lexicon correspond to picturable
objects?<o:p></o:p></span></li>
<li class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB">How can language resources be used to organize and
improve user contributed image annotations?<o:p></o:p></span></li>
<li class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB">Which are the roles of language resources in image
retrieval?<o:p></o:p></span></li>
<li class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB">How should language resources and image processing
techniques be integrated?<o:p></o:p></span></li>
<li class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB">How can current language resources be adapted for
content-based image retrieval in real-world applications, like the Web
search?<o:p></o:p></span></li>
<li class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB">Can language resources and low-level visual descriptors
be organized into a joint knowledge infrastructure?<o:p></o:p></span></li>
<li class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB">Do we need new semantic structures (ontologies, thesauri)
for CBIR? Can we build them (semi)automatically?<o:p></o:p></span></li>
<li class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB">What visual characteristics of objects can be discovered
by text processing (color, size, location, shape, texture)?<o:p></o:p></span></li>
<li class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB">What is the relation between the lexicon and image
indexing and retrieval? What words should be associated with an image?
Can this be automated?<o:p></o:p></span></li>
<li class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB">How to combine speech and textual resources related to
image data?<o:p></o:p></span></li>
<li class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB">What are some application areas where this research can
be evaluated?<o:p></o:p></span></li>
</ul>
<b style=""><span
style="font-size: 12pt; font-family: "Times New Roman";" lang="EN-GB"><br
style="page-break-before: always;" clear="all">
</span></b>
<p class="MsoNormal" style="text-align: justify;"><b style=""><span
style="" lang="EN-GB">Submissions <o:p></o:p></span></b></p>
<p class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB">We expect extended abstracts describing
research addressing one of the above questions of about 1500 words to
be
submitted as WORD, PDF or ASCII documents per email to the following
address: <a href="mailto:adrian.popescu@cea.fr">adrian.popescu@cea.fr</a><o:p></o:p></span></p>
<p class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB">A reception notification will be sent to the
authors within 48 hours. The final papers should have no more than 6
pages.<o:p></o:p></span></p>
<p class="MsoNormal" style="text-align: justify;"><span
style="font-size: 10pt;" lang="EN-GB"><o:p> </o:p></span></p>
<p class="MsoNormal" style="text-align: justify;"><b style=""><span
style="" lang="EN-GB">Important dates<o:p></o:p></span></b></p>
<table class="MsoNormalTable" style="width: 96%;" border="0"
cellpadding="0" width="96%">
<tbody>
<tr style="">
<td style="padding: 0.75pt;">
<p class="MsoNormal" style="text-align: justify;"><span style=""
lang="FR">Deadline for Abstracts<o:p></o:p></span></p>
</td>
<td style="padding: 0.75pt;">
<p class="MsoNormal" style="text-align: justify;"><span style=""
lang="FR">February 20, 2008<o:p></o:p></span></p>
</td>
</tr>
<tr style="">
<td style="padding: 0.75pt;">
<p class="MsoNormal" style="text-align: justify;"><span style=""
lang="FR">Notification of acceptance<o:p></o:p></span></p>
</td>
<td style="padding: 0.75pt;">
<p class="MsoNormal" style="text-align: justify;"><span style=""
lang="FR">March 10, 2008<o:p></o:p></span></p>
</td>
</tr>
<tr style="">
<td style="padding: 0.75pt;">
<p class="MsoNormal" style="text-align: justify;"><span style=""
lang="FR">Final Papers<o:p></o:p></span></p>
</td>
<td style="padding: 0.75pt;">
<p class="MsoNormal" style="text-align: justify;"><span style=""
lang="FR">March 31, 2008<o:p></o:p></span></p>
</td>
</tr>
<tr style="">
<td style="padding: 0.75pt;">
<p class="MsoNormal" style="text-align: justify;"><span style=""
lang="FR">Workshop<o:p></o:p></span></p>
</td>
<td style="padding: 0.75pt;">
<p class="MsoNormal" style="text-align: justify;"><span style=""
lang="FR">May 26, 2008 (afternoon session)<o:p></o:p></span></p>
</td>
</tr>
</tbody>
</table>
<p class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB"><o:p> </o:p></span></p>
<p class="MsoNormal" style="text-align: justify;"><b style=""><span
style="" lang="EN-GB">Location<o:p></o:p></span></b></p>
<p class="MsoNormal" style="text-align: justify;"><strong><span
style="font-weight: normal;" lang="FR">Palais des Congrès Mansour
Eddahbi, </span></strong><span lang="FR">Marrakech (Morocco)<b style=""><o:p></o:p></b></span></p>
<p class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB">Co-located with LREC’2008 <a
href="http://www.lrec-conf.org/lrec2008">http://www.lrec-conf.org/lrec2008</a>
<b style=""><o:p></o:p></b></span></p>
<p class="MsoNormal" style="text-align: justify;"><b style=""><span
style="" lang="EN-GB"><o:p> </o:p></span></b></p>
<p class="MsoNormal" style="text-align: justify;"><b style=""><span
style="">Organizing committee<o:p></o:p></span></b></p>
<p class="MsoNormal" style="text-align: justify;"><span style="">Thierry
Declerck, Deutsches Forschungszentrum für
Künstliche Intelligenz, Germany<o:p></o:p></span></p>
<p class="MsoNormal" style="text-align: justify;"><span style=""
lang="PL">Adrian Popescu, </span><span style="" lang="EN-GB">Commissariat
à
l’Energie Atomique </span><span style="" lang="PL">LIST, France<o:p></o:p></span></p>
<p class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB">Allan Hanbury, <st1:City w:st="on">Vienna</st1:City>
<st1:City w:st="on"><st1:place w:st="on"><st1:City w:st="on">University
of Technology</st1:City>, <st1:country-region w:st="on">Austria</st1:country-region></st1:place></st1:City><o:p></o:p></span></p>
<p class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB">Judith L. Klavans, <st1:place w:st="on"><st1:City
w:st="on">University of Maryland</st1:City>, <st1:place w:st="on">USA</st1:place></st1:place><o:p></o:p></span></p>
<p class="MsoNormal" style="text-align: justify;"><span style=""
lang="PL"><o:p> </o:p></span></p>
<p class="MsoNormal" style="text-align: justify;"><b style=""><span
style="" lang="EN-GB">Questions <o:p></o:p></span></b></p>
<p class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB">Questions about the workshop can be addressed
to: <a href="mailto:declerck@dfki.de">declerck@dfki.de</a> or <a
href="mailto:adrian.popescu@cea.fr">adrian.popescu@cea.fr</a> <o:p></o:p></span></p>
<p class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB"><o:p> </o:p></span></p>
<p class="MsoNormal" style="text-align: justify;"><b style=""><span
style="" lang="EN-GB">URL of the workshop: <a
href="http://www.dfki.de/%7Edeclerck/ontoimage.html">http://www.dfki.de/~declerck/ontoimage.html</a><o:p></o:p></span></b></p>
<p class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB"><o:p> </o:p></span></p>
<p class="MsoNormal" style="text-align: justify;"><span style=""
lang="EN-GB">The Workshop is endorsed by the European
Networks of Excellence K-Space (<a href="http://www.k-space.eu/">www.k-space.eu</a>)
and MUSCLE (<a class="moz-txt-link-freetext" href="http://www.muscle-noe.org/">http://www.muscle-noe.org/</a>)<o:p></o:p></span></p>
<pre wrap=""> </pre>
<pre class="moz-signature" cols="72">--
Thierry Declerck,
Senior Consultant at DFKI GmbH, Language Technology Lab
Stuhlsatzenhausweg, 3
D-66123 Saarbruecken
Tel: +49 (0)681 302 5358
Fax: +49 (0)681 302 5338
email: <a class="moz-txt-link-abbreviated" href="mailto:declerck@dfki.de">declerck@dfki.de</a>
-------------------------------------------------------------
Deutsches Forschungszentrum fuer Kuenstliche Intelligenz GmbH
Firmensitz: Trippstadter Strasse 122, D-67663 Kaiserslautern
Geschaeftsfuehrung:
Prof. Dr. Dr. h.c. mult. Wolfgang Wahlster (Vorsitzender)
Dr. Walter Olthoff
Vorsitzender des Aufsichtsrats:
Prof. Dr. h.c. Hans A. Aukes
Amtsgericht Kaiserslautern, HRB 2313
-------------------------------------------------------------
</pre>
</body>
</html>