<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=us-ascii">
<meta name="Generator" content="Microsoft Word 15 (filtered medium)">
<style><!--
/* Font Definitions */
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
{font-family:"Futura Std Book";
panose-1:2 11 5 2 2 2 4 2 3 3;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
margin-bottom:.0001pt;
font-size:11.0pt;
font-family:"Calibri",sans-serif;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:#0563C1;
text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
{mso-style-priority:99;
color:#954F72;
text-decoration:underline;}
span.EmailStyle17
{mso-style-type:personal-compose;
font-family:"Futura Std Book",sans-serif;
color:windowtext;
font-weight:normal;
font-style:normal;}
.MsoChpDefault
{mso-style-type:export-only;
font-family:"Calibri",sans-serif;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;}
div.WordSection1
{page:WordSection1;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]-->
</head>
<body lang="EN-US" link="#0563C1" vlink="#954F72">
<div class="WordSection1">
<p class="MsoNormal"><b><span style="font-family:"Futura Std Book",sans-serif">CIC28 5 Pillars of Color</span></b><span style="font-family:"Futura Std Book",sans-serif"> complimentary webinars focusing on the five pillars of color imaging and science. Each
presentation will run for 20-30 minutes, followed by Q&A. <o:p></o:p></span></p>
<p class="MsoNormal"><b><span style="font-family:"Futura Std Book",sans-serif"><o:p> </o:p></span></b></p>
<p class="MsoNormal"><b><span style="font-family:"Futura Std Book",sans-serif">Date:</span></b><span style="font-family:"Futura Std Book",sans-serif"> 29 October 10:00 EDT
<o:p></o:p></span></p>
<p class="MsoNormal"><b><span style="font-family:"Futura Std Book",sans-serif">Presenter:</span></b><span style="font-family:"Futura Std Book",sans-serif"> Prof. Maria Vanrell—</span>
<span style="font-family:"Futura Std Book",sans-serif">Color Encoding in Convolutional Neural Networks<o:p></o:p></span></p>
<p class="MsoNormal"><b><span style="font-family:"Futura Std Book",sans-serif">Abstract:</span></b><span style="font-family:"Futura Std Book",sans-serif"> Convolutional Neural Networks (CNN) have been proposed as suitable engines to solve computer vision problems.
Their impressive performance is a bit shadowed by their black-box nature and the consequent lack of understanding of how the visual information is internally represented. This talk shows the results of dissecting one of these networks trained on more than
a million images to perform an object recognition task.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Futura Std Book",sans-serif"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Futura Std Book",sans-serif"><a href="http://bit.ly/CIC28Webinar_29Oct">http://bit.ly/CIC28Webinar_29Oct</a><o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Futura Std Book",sans-serif">*If you are unable to attend the live webinar, a recording will be provided.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Futura Std Book",sans-serif"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Futura Std Book",sans-serif">View previous webinar recordings
<a href="http://bit.ly/CIC28_">http://bit.ly/CIC28_</a><o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Futura Std Book",sans-serif"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Futura Std Book",sans-serif">Registration is now open for CIC28 Online—IS&T Color and Imaging Conference, 4-19 November 2020.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Futura Std Book",sans-serif">View the program and register today!<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Futura Std Book",sans-serif"><a href="http://bit.ly/CIC28_">http://bit.ly/CIC28_</a><o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Futura Std Book",sans-serif"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Futura Std Book",sans-serif">Roberta Morehouse, CMP<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Futura Std Book",sans-serif">Communications and Marketing Manager<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Futura Std Book",sans-serif">Society for Imaging Science and Technology (IS&T)<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Futura Std Book",sans-serif">—imaging across applications—
<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Futura Std Book",sans-serif"> imaging.org
<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Futura Std Book",sans-serif">Connect with us on LinkedIn and Twitter @ImagingOrg #CIC28<o:p></o:p></span></p>
</div>
</body>
</html>