<div dir="ltr"><p class="MsoNormal" align="center" style="text-align:center;margin:0cm;font-size:12pt;font-family:Aptos,sans-serif"><strong><span style="font-size:10.5pt;font-family:Arial,sans-serif">CALL FOR PAPERS</span></strong><span style="font-size:10.5pt;font-family:Arial,sans-serif"><br>
<br>
<strong><i>Big Visual Data
Analytics (BVDA) Workshop</i></strong><strong> at ICIP 2024</strong><br>
<br>
<strong>IEEE International
Conference on Image Processing, 27-30 October 2024, Abu Dhabi, UAE</strong></span></p>
<p style="margin-right:0cm;margin-left:0cm;font-size:12pt;font-family:Aptos,sans-serif"><span style="font-size:10.5pt;font-family:Arial,sans-serif"> <br>
We invite researchers and practitioners working on various aspects of <strong>big visual data analytics</strong> to
submit their work to the <strong>Big
Visual Data Analytics (BVDA) Workshop</strong>, organized in conjunction
with the<strong> IEEE
International Conference on Image Processing (ICIP) 2024. </strong>The
ever-increasing visual data availability leads to repositories or streams
characterized by big data volumes, velocity (acquisition and processing speed),
variety (e.g., RGB or RGB-D or hyperspectral images) and complexity (e.g.,
video data and point clouds). Their processing necessitates novel and advanced
visual analysis methods, in order to unlock their potential across diverse
domains.<br>
<br>
The <strong>BVDA Workshop</strong> aims
to explore this rapidly evolving field encompassing cutting-edge methods,
emerging applications, and significant challenges in extracting meaning and
value from large-scale visual datasets. From high-throughput biomedical imaging
and autonomous driving sensors to satellite imagery and social media platforms,
visual data has permeated nearly every aspect of our lives. Analyzing this data
effectively requires efficient tools that go beyond traditional methods,
leveraging advancements in machine learning, computer vision and data science.
Exciting new developments in these fields are already paving the way for <strong>fully and semi-automated visual data
analysis workflows at an unprecedented scale.</strong> This
workshop will provide a platform for researchers and practitioners to discuss
recent breakthroughs and challenges in big visual data analytics, explore novel
applications across diverse domains (e.g., environment monitoring, natural
disaster management, robotics, urban planning, healthcare, etc.), as well
as for fostering interdisciplinary collaborations between computer vision, data
science, machine learning, and domain experts. Its ultimate goal is to help
identify promising research directions and pave the way for future innovations.<br>
<br>
The BVDA Workshop delves deeper into specific aspects of big visual data,
complementing the broader ICIP themes. Thus it can generate new research
interest and collaborations within the main conference community, while
attracting researchers and practitioners specifically interested in big visual
data analytics. Its interdisciplinary nature, its focus on cutting-edge areas
(e.g., large Vision-Language Models, distributed deep neural architectures,
fast generative models, etc.) and its synergies with neighboring fields (e.g.,
privacy-preserving analytics, real-time visual analytics, ethical
considerations, etc.) broaden the discussion.<br>
<br>
<strong>Topics of interest</strong> include
(non-exhaustively) the following ones:</span></p>
<ul type="disc" style="margin-bottom:0cm">
<li class="MsoNormal" style="margin:0cm;font-size:12pt;font-family:Aptos,sans-serif"><span style="font-size:10.5pt;font-family:Arial,sans-serif">Scalable
algorithms and architectures for big visual data processing and analysis.</span></li>
<li class="MsoNormal" style="margin:0cm;font-size:12pt;font-family:Aptos,sans-serif"><span style="font-size:10.5pt;font-family:Arial,sans-serif">High-performance
computing, distributed and parallel processing, efficient data storage and
retrieval for big visual data analysis.</span></li>
<li class="MsoNormal" style="margin:0cm;font-size:12pt;font-family:Aptos,sans-serif"><span style="font-size:10.5pt;font-family:Arial,sans-serif">Deep
learning architectures for large-scale visual content understanding,
search & retrieval: Convolutional Neural Networks (CNNs),
Transformers, Self-Supervised Learning, etc.</span></li>
<li class="MsoNormal" style="margin:0cm;font-size:12pt;font-family:Aptos,sans-serif"><span style="font-size:10.5pt;font-family:Arial,sans-serif">Big
visual data summarization.</span></li>
<li class="MsoNormal" style="margin:0cm;font-size:12pt;font-family:Aptos,sans-serif"><span style="font-size:10.5pt;font-family:Arial,sans-serif">Decentralized/distributed
DNN architectures for big visual data analysis.</span></li>
<li class="MsoNormal" style="margin:0cm;font-size:12pt;font-family:Aptos,sans-serif"><span style="font-size:10.5pt;font-family:Arial,sans-serif">Cloud/edge
computing architectures for big visual data analysis.</span></li>
<li class="MsoNormal" style="margin:0cm;font-size:12pt;font-family:Aptos,sans-serif"><span style="font-size:10.5pt;font-family:Arial,sans-serif">Multimodal
big visual data analysis.</span></li>
<li class="MsoNormal" style="margin:0cm;font-size:12pt;font-family:Aptos,sans-serif"><span style="font-size:10.5pt;font-family:Arial,sans-serif">Large
Vision-Language Models/Foundation Models.</span></li>
<li class="MsoNormal" style="margin:0cm;font-size:12pt;font-family:Aptos,sans-serif"><span style="font-size:10.5pt;font-family:Arial,sans-serif">Fast
generative models for visual data: Synthesizing realistic images/videos,
data augmentation, in-painting and manipulation.</span></li>
<li class="MsoNormal" style="margin:0cm;font-size:12pt;font-family:Aptos,sans-serif"><span style="font-size:10.5pt;font-family:Arial,sans-serif">Fast
Interpretability and eXplainability (XAI) of visual analytics models:
Understanding and communicating model decisions, trust and bias in AI
systems.</span></li>
<li class="MsoNormal" style="margin:0cm;font-size:12pt;font-family:Aptos,sans-serif"><span style="font-size:10.5pt;font-family:Arial,sans-serif">Privacy-preserving
analytics in the context of big visual data: Secure data processing,
differential privacy, federated learning.</span></li>
<li class="MsoNormal" style="margin:0cm;font-size:12pt;font-family:Aptos,sans-serif"><span style="font-size:10.5pt;font-family:Arial,sans-serif">Visual
analytics for real-time applications: Efficient analysis of visual
streaming data, edge/fog computing.</span></li>
<li class="MsoNormal" style="margin:0cm;font-size:12pt;font-family:Aptos,sans-serif"><span style="font-size:10.5pt;font-family:Arial,sans-serif">Visual
analytics for specialized domains: Remote sensing, natural disaster
management, medical imaging, social media analysis, etc.</span></li>
<li class="MsoNormal" style="margin:0cm;font-size:12pt;font-family:Aptos,sans-serif"><span style="font-size:10.5pt;font-family:Arial,sans-serif">Ethical
considerations in big visual data analytics: Data ownership, fairness,
accountability, societal impact.</span></li>
</ul>
<p style="margin-right:0cm;margin-left:0cm;font-size:12pt;font-family:Aptos,sans-serif"><span style="font-size:10.5pt;font-family:Arial,sans-serif"> <br>
The regular ICIP paper template/style must be used for submission. All accepted
contributions will be <strong>published
in IEEE Xplore</strong>. The paper submission deadline is <strong>May</strong> <strong>13, 2024</strong>.<br>
<br>
<strong>For further details and
submission instructions visit: </strong><a href="https://icarus.csd.auth.gr/cfp-bvda-icip24-workshop/" target="_blank" style="color:blue">https://icarus.csd.auth.gr/cfp-bvda-icip24-workshop/</a><br>
<br>
<br>
Organizers<br>
<br>
Prof. Ioannis Pitas: Chair of the International AI Doctoral Academy (<a href="https://www.i-aida.org/" target="_blank" title="https://www.i-aida.org/" style="color:blue">AIDA</a>),
Director of the Artificial Intelligence and Information analysis (<a href="https://aiia.csd.auth.gr/" target="_blank" title="https://aiia.csd.auth.gr/" style="color:blue">AIIA</a>) Lab,<br>
Aristotle University of Thessaloniki, Greece.<br>
<br>
Prof. Massimo Villari: University of Messina, Italy.<br>
<br>
Dr. Ioannis Mademlis: Postdoctoral researcher at the Harokopio University of
Athens.</span></p></div>