<div dir="ltr"><div class="gmail_default" style="font-family:verdana,sans-serif"><span style="color:rgb(0,0,0)">Apologies for crossposting!</span></div><div class="gmail_default" style="font-family:verdana,sans-serif"><span style="color:rgb(0,0,0)"><br></span></div><div class="gmail_default" style="font-family:verdana,sans-serif"><span style="color:rgb(0,0,0)">Deep Declarative Networks
CVPR 2020 Workshop -- Call for Papers</span><br></div><div class="gmail_quote"><div dir="ltr"><div class="gmail_quote"><div dir="ltr"><div><font color="#000000" face="verdana, sans-serif">*****************************************************</font></div><div><font color="#000000" face="verdana, sans-serif"><br></font></div><div><div><font color="#000000" face="verdana, sans-serif">Website: <a href="http://cvpr2020.deepdeclarativenetworks.com/" target="_blank">http://cvpr2020.deepdeclarativenetworks.com/</a></font></div><div><font color="#000000" face="verdana, sans-serif">Submission Deadline: 1st March 2020</font></div><div><font color="#000000" face="verdana, sans-serif">Workshop on 14th June 2020 in conjunction with CVPR 2020, Seattle, WA</font></div><div><font color="#000000" face="verdana, sans-serif">Contact us at </font><font face="verdana, sans-serif"><a href="mailto:cvpr2020@deepdeclarativenetworks.com" target="_blank">cvpr2020@deepdeclarativenetworks.com</a></font></div><div><font color="#000000" face="verdana, sans-serif"><br></font></div><div><font color="#000000" face="verdana, sans-serif">*****************************************************</font></div></div><div><font color="#000000" face="verdana, sans-serif"><br></font></div><div><font color="#000000" face="verdana, sans-serif">ABOUT</font></div><div><font color="#000000" face="verdana, sans-serif">******</font></div><div><font color="#000000" face="verdana, sans-serif">Conventional deep learning architectures involve composition of simple feedforward processing functions that are
explicitly defined. Recently, researchers have been exploring deep learning models with implicitly defined
components, where the output of the node involves solving an optimization problem in the forward pass. To
distinguish these from conventional deep learning models, we call them deep declarative networks, borrowing
nomenclature from the programming languages community.<br></font></div><div><font color="#000000" face="verdana, sans-serif"><br></font></div><div><font color="#000000" face="verdana, sans-serif">This workshop explores the advantages (and potential shortcomings) of declarative networks and their variants,
bringing ideas developed in different contexts under the umbrella of deep declarative networks. We will discuss
technical issues that need to be overcome in developing such models and applications of these models to computer
vision problems that show benefit over conventional approaches. For details on the topics, program, and speakers, please visit </font><a href="http://cvpr2020.deepdeclarativenetworks.com/" target="_blank"><font face="verdana, sans-serif">http://cvpr2020.deepdeclarativenetworks.com/</font><font color="#000000" face="verdana, sans-serif"><br></font></a></div><div><font face="verdana, sans-serif"><br></font></div><div><div><font face="verdana, sans-serif">TOPICS</font></div><div><font face="verdana, sans-serif">******</font></div></div><div><font color="#000000" face="verdana, sans-serif">We invite paper submissions of up to four (4) pages describing work in related areas including: </font></div><div><font color="#000000" face="verdana, sans-serif"><span class="gmail_default"> * </span>Declarative end-to-end learnable processing nodes </font></div><div><font color="#000000" face="verdana, sans-serif"><span class="gmail_default"> * </span>Differentiable constrained and unconstrained (non-convex) optimization problems </font></div><div><font color="#000000" face="verdana, sans-serif"><span class="gmail_default"> *</span> Differentiable convex optimization problems and techniques </font></div><div><font color="#000000" face="verdana, sans-serif"><span class="gmail_default"> *</span> Imposing hard constraints in deep learning models </font></div><div><font color="#000000" face="verdana, sans-serif"><span class="gmail_default"> *</span> Backpropagation through statistical and physic<span class="gmail_default">s</span> models </font></div><div><font color="#000000" face="verdana, sans-serif"><span class="gmail_default"> *</span> Applications of the above to problems in computer vision<span class="gmail_default">, such as</span></font></div><div><font color="#000000" face="verdana, sans-serif"><span class="gmail_default"> ** </span> differentiable rendering</font></div><div><font color="#000000" face="verdana, sans-serif"><span class="gmail_default"> ** </span>differentiable 3d
models </font></div><div><font color="#000000" face="verdana, sans-serif"><span class="gmail_default"> ** </span>reinforcement learning</font></div><div><font color="#000000" face="verdana, sans-serif"><span class="gmail_default"> ** </span>action recognition</font></div><div><font color="#000000" face="verdana, sans-serif"><span class="gmail_default"> ** </span>meta-learning, etc<span class="gmail_default">.</span><br></font></div><div></div><div><font color="#000000" face="verdana, sans-serif"><br></font></div><div><font color="#000000" face="verdana, sans-serif"><span class="gmail_default">SUBMISSIONS</span></font></div><div><font color="#000000" face="verdana, sans-serif"><span class="gmail_default">************</span></font></div><div><font color="#000000" face="verdana, sans-serif"><span class="gmail_default"></span>Accepted submissions will be presented as short orals or posters at the workshop and will appear on the workshop
website. Authors will be given an opportunity to revise the submission before posting on the website. </font></div><div><font color="#000000" face="verdana, sans-serif"><br></font></div><div><font color="#000000" face="verdana, sans-serif">Papers should
follow the CVPR formatting guidelines and emailed as a single PDF to <a href="mailto:cvpr2020@deepdeclarativenetworks.com" target="_blank">cvpr2020@deepdeclarativenetworks.com</a>, with
subject line “Paper: ”. Submissions are not anonymous (and should include all authors’ names and affiliations).
References are to be included in the 4-page limit.<span class="gmail_default"> We encourage submissions of preliminary or ongoing work. Accepted papers **will not appear** in the official IEEE
proceedings. Relevant work that has previously been published or is to be presented at the main conference is also
welcome.</span><br></font></div><div><font color="#000000" face="verdana, sans-serif"><br></font></div><div><div><font color="#000000" face="verdana, sans-serif">IMPORTANT DATES</font></div><div><font color="#000000" face="verdana, sans-serif">****************</font></div><div><font color="#000000" face="verdana, sans-serif">Submission deadline: 1st March 2020</font></div><div><font color="#000000" face="verdana, sans-serif">Author Notification: 22nd March 2020</font></div><div><font color="#000000" face="verdana, sans-serif">Camera-ready deadline: 1st May 2020</font></div><div><font color="#000000" face="verdana, sans-serif">Workshop date: 14th June 2020</font></div><font color="#000000" face="verdana, sans-serif"><br></font></div><div><div><font color="#000000" face="verdana, sans-serif">Organizers: Stephen Gould<span class="gmail_default" style="font-family:verdana,sans-serif"> (ANU)</span>, Anoop Cherian<span class="gmail_default" style="font-family:verdana,sans-serif"> (MERL)</span>, Dylan Campbell<span class="gmail_default" style="font-family:verdana,sans-serif"> (ANU)</span>, and Richard Hartley<span class="gmail_default" style="font-family:verdana,sans-serif"> (ANU)</span></font></div></div><div><font color="#000000" face="verdana, sans-serif">Email: <a href="mailto:cvpr2020@deepdeclarativenetworks.com" target="_blank">cvpr2020@deepdeclarativenetworks.com</a> </font></div><div><font color="#000000" face="verdana, sans-serif">Website: <a href="http://cvpr2020.deepdeclarativenetworks.com/" target="_blank">http://cvpr2020.deepdeclarativenetworks.com/ </a></font></div>
<div><font color="#000000" face="verdana, sans-serif"><br></font></div><font color="#000000" face="verdana, sans-serif">-- <br></font><div dir="ltr" data-smartmail="gmail_signature"><div dir="ltr"><div><font color="#000000" face="verdana, sans-serif">Thank you,</font></div><div><font color="#000000" face="verdana, sans-serif"><br></font></div><div><font color="#000000" face="verdana, sans-serif">Anoop Cherian</font></div><div><font color="#000000" face="verdana, sans-serif">Research Scientist</font></div><div><font color="#000000" face="verdana, sans-serif">Mitsubishi Electric Research Labs<span class="gmail_default" style="font-family:verdana,sans-serif"> (MERL)</span></font></div><div><font color="#000000" face="verdana, sans-serif">Cambridge, MA</font></div><div><font face="verdana, sans-serif"><font color="#000000">Website: </font></font><font face="verdana, sans-serif"><a href="https://www.merl.com/people/cherian" target="_blank">https://www.merl.com/people/cherian</a></font></div></div></div></div></div></div></div><div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div style="font-family:verdana,sans-serif"></div></div></div></div>