<div dir="ltr">
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN-US">=================================================================<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN-US">CALL FOR </span><span>CHALLENGE<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span>HYPER SPECTRAL CITY
V1.0 CHALLENGE <span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span>In Conjunct with </span><span lang="EN-US">The 2nd Workshop on Physics Based Vision Meets Deep Learning (PBDL2019)<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN-US">In Conjunction, November 2, Seoul, Korea<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN-US"><a href="https://pbdl2019.github.io/">https://pbdl2019.github.io/</a><span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN-US">------------------------------------------------------------<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span>We propose a semantic
segmentation challenge for urban autonomous driving scene which utilizes newly
developed hyperspectral camera. The motivation is to compensate the
insufficient visual quality problem of existing dataset. Particularly, the
CityScape[1] dataset provides only extremely washed out RGB images. To solve
this, we endeavour to propose the new dataset which adopts multi-channel visual
input. Our new dataset, can provide the following benefits: 1. properly
balanced and colourful visual input. 2. We can analyse and see visual
properties which cannot be seen from RGB channels. 3. We can robustly handle
night scenes, thanks to the near infrared band. 4. We can robustly handle water
phenomenon including rain and fog, because of the absolution behaviour in the
infrared band.<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span><span> </span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span>For the initial
release of the dataset, we decide to propose the task of semantic segmentation
with coarse labeling. We release 367 frames hyperspectral images with coarse
labeling for training and 67 frames with fine labeling for testing.<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN-US"><span> </span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN-US"><span> </span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN-US">------------------------------------------------------------<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN-US">Important Dates:<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN-US"><span> </span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN-US"><span> </span>-
Site open and training datset avaialbe for download: July 25,2019<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN-US"><span> </span>-
Testing dataset avaialbe for download, challenge open for submission: Aug
8,2019<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN-US"><span> </span>-
Challenge close: Aug 28,2019<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN-US">------------------------------------------------------------<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN-US">Access: <span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN-US">The dataset access is through registration
at: <a href="http://pbdl2019.natapp1.cc/download">http://pbdl2019.natapp1.cc/download</a><span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN">The Dataset is
for this challenge and research purpose only. Commercial use is not permitted.<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN"><span> </span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN">If participants
would like to use dataset in this challenge to produce academic outputs, this
document must be cited:<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN"><span> </span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN">[1]"Hyperspectral
City V1.0 Dataset and Benchmark”, Shaodi You*, arXiv:1907.10270.<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN"><span> </span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN">E-mail
<a href="mailto:pbdl.ws@outlook.com">pbdl.ws@outlook.com</a> if you have any technical problems.<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN-US">------------------------------------------------------------<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN-US">Organizers:<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><a name="OLE_LINK18"><span lang="EN-US">Yu Li</span></a><span lang="EN-US">, Tencent, China<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><a name="OLE_LINK14"></a><a name="OLE_LINK13"><span><span lang="EN-US">Ying Fu</span></span></a><span lang="EN-US">, <a name="OLE_LINK17"></a><a name="OLE_LINK16"></a><a name="OLE_LINK15"><span><span>Beijing Institute of Technology</span></span></a>, China<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><a name="OLE_LINK4"></a><a name="OLE_LINK3"><span><span lang="EN-US">Shaodi You</span></span></a><span lang="EN-US">, <a name="OLE_LINK6"></a><a name="OLE_LINK5"><span>Data61-CSIRO</span></a>, Australia<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN-US">Yinqiang Zheng, National Institute of
Informatics, Japan<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN-US">Feng Lu, Beihang University, China<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><a name="OLE_LINK11"></a><a name="OLE_LINK10"><span><span lang="EN-US">Boxin Shi</span></span></a><span lang="EN-US">, Peking University, China<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN-US">Robby T. Tan, Yale-NUS College & <a name="OLE_LINK2"></a><a name="OLE_LINK1"><span>National
University of Singapore, Singapore</span></a><span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN-US">------------------------------------------------------------<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN-US">Contact:<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN-US">For any inquiries regarding the workshop,
please contact:</span><span lang="EN-US"> </span><span lang="EN-US"><a href="mailto:pbdl.ws@gmail.com" style="color:rgb(0,115,174);text-decoration:none"><span>pbdl.ws@gmail.com</span></a></span><span lang="EN-US"><span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN">E-mail
<a href="mailto:pbdl.ws@outlook.com">pbdl.ws@outlook.com</a> if you have any technical problems.<span></span></span></p>
<p class="MsoNormal" style="margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:"Calibri",sans-serif"><span lang="EN-US">=================================================================<span></span></span></p>
<br clear="all"><br>-- <br><div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature">YOU, Shaodi<br><a href="mailto:youshaodi@gmail.com" target="_blank">youshaodi@gmail.com</a><br><br></div></div>