<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=Windows-1252">
<style type="text/css" style="display:none;"> P {margin-top:0;margin-bottom:0;} </style>
</head>
<body dir="ltr">
<div style="font-family: Calibri, Arial, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">ECCV 2020 - Workshop on </span><span lang="en-US">Adversarial Robustness in the Real World</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">Glasgow- Scotland - 23th August 2020</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">In conjunction with <span>ECCV</span> 2020 - European Conference on Computer Vision</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US"> Web: </span><a href="https://eccv20-adv-workshop.github.io" rel="nofollow" target="_blank"><span lang="en-US">https://eccv20-adv-workshop.<wbr>github.io</span></a><span lang="en-US"></span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US"> </span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">******************************<wbr>**************************</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">_________________</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">IMPORTANT DATES</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">_________________</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US"> </span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">Full Paper Submission: July 10th 2020, Anywhere on Earth (AoE)</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">Notification of Acceptance: July 30th, 2020, Anywhere on Earth (AoE)</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US"> </span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">________________</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">CALL FOR PAPERS</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">________________</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US"> </span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">Computer vision systems nowadays have advanced performance but research in adversarial machine learning also shows that they are not as robust as the human vision system. In this context, perturbation-based adversarial examples have received
great attention. Moreover, recent work has shown that real-world adversarial examples exist when objects are partially occluded or viewed in previously unseen poses and environments (such as different weather conditions). Discovering and harnessing those adversarial
examples provides opportunities for understanding and improving computer vision systems in real-world environments. In particular, deep models with structured internal representations seem to be a promising approach to enhance robustness in the real world,
while also being able to explain their predictions. </span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">In this workshop, we aim to bring together researches from the fields of adversarial machine learning, robust vision and explainable AI to discuss recent research and future directions for adversarial robustness and explainability, with a
particular focus on real-world scenarios.</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">We invite submissions on <b>any aspect of adversarial robustness in real-world computer vision</b>. This includes, but is not limited to:</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">- Discovery of real-world adversarial examples</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">- Novel architectures with robustness to occlusion, viewpoint and other real-world domain shifts</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">- Domain adaptation techniques for building robust vision system in the real world</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">- Datasets for evaluating model robustness</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">- Adversarial machine learning for diagnosing and understanding limitations of computer vision systems</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">- Improving generalization performance of computer vision systems to out-of-distribution samples</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">- Structured deep models</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">- Explainable AI</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US"> </span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">_________________</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">INVITED SPEAKERS</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">_________________</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US"> </span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">- Matthias Bethge, University of Tübingen, Germany</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span style="color:windowtext" lang="en-US">- </span><span style="color:windowtext" lang="en-US">Alan Yuille, Johns Hopkins University, USA</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span><span lang="en-US">- Andreas Geiger, University of Tübingen, Germany</span></span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span><span lang="en-US">- Raquel Urtasun, University of Toronto, Canada</span></span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span style="color:windowtext" lang="en-US">- Honglak Lee, University of Michigan, USA</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span style="color:windowtext" lang="en-US">- Bo Li, </span><span><span lang="en-US">University of Illinois at Urbana-Champaign, USA</span></span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span><span lang="en-US">- Judy Hoffman, Georgia Tech, USA</span></span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span><span lang="en-US">- Daniel Fremont, UC Santa Cruz, USA</span></span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span><span lang="en-US">- George J. Pappas, University of Pennsylvania<br>
</span></span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US"> </span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">____________</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">SUBMISSION AND REVISION</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">____________</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US"> </span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">All submissions will be handled electronically via the conference’s CMT Website:
</span><a href="https://cmt3.research.microsoft.com/AROW2020/" rel="nofollow" target="_blank"><span lang="en-US">https://cmt3.research.<wbr>microsoft.com/AROW2020/</span></a><span lang="en-US"></span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US"> </span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">The format for paper submission is the same as the <span>ECCV</span> 2020 main conference. Submissions need to be anonymized and follow the
</span><a href="https://eccv2020.eu/author-instructions/" rel="nofollow" target="_blank"><span lang="en-US">ECCV 2020 Author Instructions</span></a><span lang="en-US">:</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<a href="https://eccv2020.eu/author-instructions/" rel="nofollow" target="_blank"><span lang="en-US">https://eccv2020.eu/author-<wbr>instructions/</span></a><span lang="en-US"></span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US"> </span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">AROW reviewing will be double-blind. Each submission will be reviewed by at least three reviewers for originality, significance, clarity, soundness, relevance and technical contents.</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US"> </span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">The workshop considers two types of submissions: (1) Long Paper: Papers are limited to 14 pages excluding references and will be included in the official ECCV proceedings; (2) Extended Abstract: Papers are limited to 7 pages excluding references
and will NOT be included in the official ECCV proceedings. Based on the PC recommendations, the accepted long papers/extended abstracts will be allocated either a contributed talk or a poster presentation. </span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US"> </span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">Authors may optionally submit additional material that could not be included in the main paper due to constraints of format (e.g., a video), space (e.g., a proof of a theorem or an extra figure or table) or anonymity.</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US"> _________________</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">WORKSHOP ORGANIZERS</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">_________________</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US"> </span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">Adam Kortylewski, Johns Hopkins University, USA</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">Cihang Xie, Johns Hopkins University, USA</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">Song Bai, University of Oxford, UK</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span>Zhaowei Cai, Amazon, USA</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span>Yingwei Li, Johns Hopkins University, USA</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span>Andrei Barbu, MIT, USA</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">Wieland Brendel, University of Tübingen, Germany</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">Nuno Vasconcelos, UCSD, USA</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">Andrea Vedaldi, University of Oxford, UK</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">Philip H.S. Torr, University of Oxford, UK</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">Rama Chellappa, University of Maryland, USA</span></p>
<p style="color:black;font-size:11pt;font-family:Calibri,sans-serif;margin:0 0 8pt 0;line-height:107%">
<span lang="en-US">Alan Yuille, Johns Hopkins University, USA</span></p>
<br>
</div>
</body>
</html>