<html 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=utf-8">
<meta name="Title" content="">
<meta name="Keywords" content="">
<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:"MS Gothic";
panose-1:2 11 6 9 7 2 5 8 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0cm;
margin-bottom:.0001pt;
font-size:12.0pt;
font-family:Calibri;
mso-fareast-language:EN-US;}
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;
font-family:Calibri;
color:windowtext;}
span.EmailStyle18
{mso-style-type:personal-reply;
font-family:Calibri;
color:windowtext;}
span.msoIns
{mso-style-type:export-only;
mso-style-name:"";
text-decoration:underline;
color:teal;}
.MsoChpDefault
{mso-style-type:export-only;
font-size:10.0pt;}
@page WordSection1
{size:612.0pt 792.0pt;
margin:3.0cm 2.0cm 3.0cm 2.0cm;}
div.WordSection1
{page:WordSection1;}
--></style>
</head>
<body bgcolor="white" lang="EN-GB" link="#0563C1" vlink="#954F72">
<div class="WordSection1">
<p class="MsoNormal" style="text-align:justify"><span style="font-size:11.0pt;font-family:"Times New Roman";color:black;mso-fareast-language:EN-GB">Call for paper</span><o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify"><span style="font-size:11.0pt;font-family:"Times New Roman";color:black;mso-fareast-language:EN-GB">CVPR 2017 workshop on</span><o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify"><span style="font-size:11.0pt;font-family:"Times New Roman";color:black;mso-fareast-language:EN-GB">DeepVision: Temporal Deep Learning (TDL)
</span><o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify"><span style="font-family:"Times New Roman";color:black;mso-fareast-language:EN-GB"><a href="http://deep-vision.net/">http://deep-vision.net/</a></span><o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify"><span style="font-family:"Times New Roman";color:black;mso-fareast-language:EN-GB">26 July 2017, Honolulu, Hawaii, USA</span><o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify"><span style="font-family:"Times New Roman";color:black;mso-fareast-language:EN-GB"> </span><o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify"><span style="font-size:11.0pt;font-family:"Times New Roman";color:black;mso-fareast-language:EN-GB">The computer vision community over the past few years has been dominated by deep learning based techniques. These
techniques have, however, been mostly focused on still images, although many new publicly available data and high impact applications benefit from video recordings. Videos contain valuable temporal information that can be exploited to achieve better performance.
Exploiting temporal information is of great importance in computer vision applications, like object tracking and recognition, scene analysis and understanding, etc. Deep learning based techniques are challenged to employ temporal information in such applications.
Although some advances have been performed in this direction, mainly involving 3D convolutions, motion-based input features, or deep temporal- based models such as RNN-LSTM, significant advances are expected to be performed in this field. </span><span style="font-size:11.0pt;font-family:"MS Gothic";color:black;mso-fareast-language:EN-GB">
</span><span style="font-size:11.0pt;font-family:"Times New Roman";color:black;mso-fareast-language:EN-GB">Papers
on <b>deep learning </b>techniques utilizing <b>temporal </b>information on any of the following topics can be covered by the workshop:</span><o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify"><span style="font-size:11.0pt;font-family:"Times New Roman";color:black;mso-fareast-language:EN-GB">TDL object recognition </span><span style="font-size:11.0pt;font-family:"MS Gothic";color:black;mso-fareast-language:EN-GB">
</span><o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify"><span style="font-size:11.0pt;font-family:"Times New Roman";color:black;mso-fareast-language:EN-GB">TDL object tracking </span><span style="font-size:11.0pt;font-family:"MS Gothic";color:black;mso-fareast-language:EN-GB">
</span><o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify"><span style="font-size:11.0pt;font-family:"Times New Roman";color:black;mso-fareast-language:EN-GB">TDL scene analysis </span><span style="font-size:11.0pt;font-family:"MS Gothic";color:black;mso-fareast-language:EN-GB">
</span><o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify"><span style="font-size:11.0pt;font-family:"Times New Roman";color:black;mso-fareast-language:EN-GB">TDL shape analysis </span><span style="font-size:11.0pt;font-family:"MS Gothic";color:black;mso-fareast-language:EN-GB">
</span><o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify"><span style="font-size:11.0pt;font-family:"Times New Roman";color:black;mso-fareast-language:EN-GB">TDL crowd analysis </span><span style="font-size:11.0pt;font-family:"MS Gothic";color:black;mso-fareast-language:EN-GB">
</span><o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify"><span style="font-size:11.0pt;font-family:"Times New Roman";color:black;mso-fareast-language:EN-GB">TDL human body motion analysis </span><span style="font-size:11.0pt;font-family:"MS Gothic";color:black;mso-fareast-language:EN-GB">
</span><o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify"><span style="font-size:11.0pt;font-family:"Times New Roman";color:black;mso-fareast-language:EN-GB">TDL facial analysis systems </span><span style="font-size:11.0pt;font-family:"MS Gothic";color:black;mso-fareast-language:EN-GB">
</span><o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify"><span style="font-size:11.0pt;font-family:"Times New Roman";color:black;mso-fareast-language:EN-GB">New TDL models </span><span style="font-size:11.0pt;font-family:"MS Gothic";color:black;mso-fareast-language:EN-GB">
</span><o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify"><span style="font-size:11.0pt;font-family:"Times New Roman";color:black;mso-fareast-language:EN-GB">New applications of TDL </span><span style="font-size:11.0pt;font-family:"MS Gothic";color:black;mso-fareast-language:EN-GB">
</span><o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify"> <o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify">The submitted papers are limited to eight pages, including figures and tables, in the CVPR style. Additional pages containing only cited references are allowed. CVPR guidelines and templates given in the following
page should be used:<o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify"><a href="http://cvpr2017.thecvf.com/submission/main_conference/author_guidelines">http://cvpr2017.thecvf.com/submission/main_conference/author_guidelines</a><o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify"> <o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify">The accepted papers will be presented as posters at deep vision workshop and will be published in CVPR proceedings.
<o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify"> <o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify">Important dates:<o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify">Important dates:<o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify">Submission deadline: March 31st<o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify">Decision to authors: April 21st<o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify">Camera ready: April 28th<o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify">Submission through CMT at:<o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify"><a href="https://cmt3.research.microsoft.com/DV2017/">https://cmt3.research.microsoft.com/DV2017/</a><o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify"> <o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify"> <o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify"> <o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify">Organizing committee:<o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify">Kamal Nasrollahi (primary contact regarding paper submission: kn@create.aau.dk), Jose Alvarez Lopez, Sergio Escalera, Nathan Silberman, Ajmal Mian, Dhruv Batra, Gholamreza Anbarjafari, Yann LeCun , and Thomas
B. Moeslund<o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify"> <o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify"><b>Invited Speakers:</b><o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify">DeepVision:<o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify">Gabriel Kreiman<o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify">Sanja Fidler<o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify">Raia Hadsell<o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify">Hugo Larochelle<o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify">Lior Wolf<o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify">Temporal Deep Learning:<o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify">Maja Pantic<o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify">Trevor Darrell<o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify">Xiaogang Wang<o:p></o:p></p>
<p class="MsoNormal" style="text-align:justify"> <o:p></o:p></p>
<p class="MsoNormal"> <o:p></o:p></p>
<p class="MsoNormal"><span style="font-size:11.0pt"> </span><o:p></o:p></p>
</div>
</body>
</html>