<div dir="ltr"><p class="MsoNormal" align="center" style="text-align:center;line-height:75%;margin:0cm 0cm 0.0001pt;font-size:10.5pt;font-family:Calibri,sans-serif"><b><span lang="EN-US" style="font-size:15pt;line-height:75%;font-family:"Times New Roman",serif">Call
for Papers</span></b></p>

<p class="MsoNormal" align="center" style="text-align:center;line-height:75%;margin:0cm 0cm 0.0001pt;font-size:10.5pt;font-family:Calibri,sans-serif"><b><span lang="EN-US" style="font-size:15pt;line-height:75%;font-family:"Times New Roman",serif">Special
Issue of IEEE Transactions on Multimedia</span></b></p>

<p class="MsoNormal" align="center" style="text-align:center;line-height:75%;margin:0cm 0cm 0.0001pt;font-size:10.5pt;font-family:Calibri,sans-serif"><b><span lang="EN-US" style="font-size:15pt;line-height:75%;font-family:"Times New Roman",serif">“Weakly
Supervised Learning for Image and Video Understanding”</span></b></p>

<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-family:"Times New Roman",serif"> </span></p>

<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><a name="OLE_LINK5"><b><span lang="EN-US" style="font-size:14pt;font-family:"Times New Roman",serif">SUMMARY:</span></b></a><b><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif"></span></b></p>

<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif">With the goal of
addressing fine-level image and video understanding tasks by learning from
coarse-level human annotations, WSL is of particular importance in such a big
data era as it can dramatically alleviate the human labor for annotating each
of the structured visual/multimedia data and thus enables machines to learn
from much larger-scaled data but with the equal annotation cost of the
conventional fully supervised learning methods. More importantly, when dealing
with the data from real-world application scenarios, such as the medical
imaging data, remote sensing data, and audio-visual data, fine-level manual
annotations are very limited and difficult to obtain. Under these
circumstances, the WSL-based learning frameworks, specifically for the
WSL-based multi-modality/multi-task learning frameworks, would bring great
benefits. Unfortunately, designing effective WSL systems is challenging due to
the issues of “semantic unspecificity” and “instance ambiguity”, where the
former refers to the setting where the provided semantic label is at image
level rather than specific instance-level while the latter refers to the
ambiguity when determining an instance sample against the instance part or
instance cluster. Principled solutions to address these problems are still
under-studied. Nowadays, with the rapid development of advanced machine
learning techniques, such as the Graph Convolutional Networks, Capsule
Networks, Transformers, Generative Adversarial Networks, and Deep Reinforcement
Learning models, new opportunities have emerged for solving the problems in WSL
and applying WSL to richer vision and multimedia tasks. </span><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif">This
special issue aims at promoting cutting-edge research along this direction and
offers a timely collection of works to benefit researchers and practitioners.
We welcome high-quality original submissions addressing both novel theoretical
and practical aspects related to WSL, as well as the real-world applications
based on WSL approaches. </span></p>

<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif"> </span></p>

<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><b><span lang="EN-US" style="font-size:14pt;font-family:"Times New Roman",serif">SCOPE:</span></b></p>

<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif">Topics
of interests include, but are not limited to:</span></p>

<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt 18pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt">-<span style="font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;font-size:7pt;line-height:normal;font-family:"Times New Roman"">         
</span></span><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif">Multi-modality weakly supervised learning
theory and framework;</span></p>

<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt 18pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt">-<span style="font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;font-size:7pt;line-height:normal;font-family:"Times New Roman"">         
</span></span><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif">Multi-task weakly supervised learning
theory and framework;</span></p>

<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt 18pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt">-<span style="font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;font-size:7pt;line-height:normal;font-family:"Times New Roman"">         
</span></span><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif">Robust learning theory and framework; </span></p>

<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt 18pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt">-<span style="font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;font-size:7pt;line-height:normal;font-family:"Times New Roman"">         
</span></span><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif">Audio-visual learning under weak
supervision;</span></p>

<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt 18pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt">-<span style="font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;font-size:7pt;line-height:normal;font-family:"Times New Roman"">         
</span></span><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif">Weakly supervised spatial/temporal feature
learning;</span></p>

<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt 18pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt">-<span style="font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;font-size:7pt;line-height:normal;font-family:"Times New Roman"">         
</span></span><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif">Self-supervised learning frameworks and
applications;</span></p>

<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt 18pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt">-<span style="font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;font-size:7pt;line-height:normal;font-family:"Times New Roman"">  </span></span><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif">Graph Convolutional Networks/Graph Neural
Networks-based weakly supervised learning frameworks;</span></p>

<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt 18pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt">-<span style="font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;font-size:7pt;line-height:normal;font-family:"Times New Roman"">         
</span></span><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif">Deep Reinforcement Learning for weakly
supervised learning;</span></p>

<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt 18pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt">-<span style="font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;font-size:7pt;line-height:normal;font-family:"Times New Roman"">         
</span></span><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif">Emerging vision and multimedia tasks with
limited supervision;</span></p>

<p class="gmail-MsoListParagraph" style="margin:0cm 0cm 0.0001pt 18pt;text-indent:0cm;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif"> </span></p>

<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><b><span lang="EN-US" style="font-size:14pt;font-family:"Times New Roman",serif">IMPORTANT DATESs: </span></b><b><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif"> </span></b></p>

<p class="MsoNormal" style="text-indent:21pt;margin:0cm 0cm 0.0001pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif">Manuscript
submission:           15^th January
2021  </span></p>

<p class="MsoNormal" style="text-indent:21pt;margin:0cm 0cm 0.0001pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif">Preliminary
results:                  15^thApril
2021</span></p>

<p class="MsoNormal" style="text-indent:21pt;margin:0cm 0cm 0.0001pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif">Revisions due:                          1^st June 2021</span></p>

<p class="MsoNormal" style="text-indent:21pt;margin:0cm 0cm 0.0001pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif">Notification:                             15^th July 2021</span></p>

<p class="MsoNormal" style="text-indent:21pt;margin:0cm 0cm 0.0001pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif">Final manuscripts
due:             15^th August 2021
</span></p>

<p class="MsoNormal" style="text-indent:21pt;margin:0cm 0cm 0.0001pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif">Anticipated
publication:           4^th quarter
of 2021</span></p>

<p class="MsoNormal" style="text-indent:21pt;margin:0cm 0cm 0.0001pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif"> </span></p>

<p class="MsoNormal" style="text-indent:21pt;margin:0cm 0cm 0.0001pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif"> </span></p>

<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><b><span lang="EN-US" style="font-size:14pt;font-family:"Times New Roman",serif">SUBMISSION
PROCEDURE:</span></b></p>

<p class="MsoNormal" style="text-indent:21pt;margin:0cm 0cm 0.0001pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif">Papers should be
formatted according to the IEEE Transactions on Multimedia guidelines for
authors (see: <a href="http://www.signalprocessingsociety.org/tmm/tmm-author-info/">http://www.signalprocessingsociety.org/tmm/tmm-author-info/</a>). By
submitting/resubmitting your manuscript to these Transactions, you are
acknowledging that you accept the rules established for publication of
manuscripts, including agreement to pay all over-length page charges, color
charges, and any other charges and fees associated with publication of the
manuscript. Manuscripts (both 1-column and 2-column versions are required)
should be submitted electronically through the online IEEE manuscript
submission system at <a href="http://mc.manuscriptcentral.com/tmm-ieee">http://mc.manuscriptcentral.com/tmm-ieee</a>. When selecting a
manuscript type, the authors must choose WSL Special Issue. All submitted
papers will go through the same review process as the regular TMM paper
submissions. Referees will consider originality, significance, technical
soundness, clarity of exposition, and relevance to the special issue topics
above.</span></p>

<p class="MsoNormal" style="text-indent:21pt;margin:0cm 0cm 0.0001pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif"> </span></p>

<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><b><span lang="EN-US" style="font-size:14pt;font-family:"Times New Roman",serif">GUEST EDITORS:</span></b></p>

<p class="MsoNormal" style="text-indent:21pt;margin:0cm 0cm 0.0001pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif">Dingwen Zhang,
Xidian University, China</span></p>

<p class="MsoNormal" style="text-indent:21pt;margin:0cm 0cm 0.0001pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif">Chuang Gan, MIT
and MIT-IBM Watson AI Lab, USA</span></p>

<p class="MsoNormal" style="text-indent:21pt;margin:0cm 0cm 0.0001pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif">Enrico Magli, Politecnico
di Torino, Italy</span></p>

<p class="MsoNormal" style="text-indent:21pt;margin:0cm 0cm 0.0001pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif">David Crandall, Indiana
University, USA</span></p>

<p class="MsoNormal" style="text-indent:21pt;margin:0cm 0cm 0.0001pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif">Junwei Han,
Northwestern Polytechnical University, China</span></p>

<p class="MsoNormal" style="text-indent:21pt;margin:0cm 0cm 0.0001pt;text-align:justify;font-size:10.5pt;font-family:Calibri,sans-serif"><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif">Fatih
Porikli, Australian National University, Australia</span></p><div><br></div>-- <br><div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div><div dir="ltr">Dingwen Zhang<div><a href="https://zdw-nwpu.github.io/dingwenz.github.com/" target="_blank">https://zdw-nwpu.github.io/dingwenz.github.com/</a><br></div><div>Xidian University</div><div>Carnegie Mellon University</div></div></div></div></div></div>