<!DOCTYPE html>
<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
</head>
<body>
<div><i>Apologies for multiple posting. Please feel free to forward
to whom may be interested.</i></div>
<h3 id="exfma"
style="color: rgb(0, 0, 0); font-family: "Times New Roman"; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: rgb(255, 255, 255); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;"></h3>
<h3 id="exfma"
style="color: rgb(0, 0, 0); font-family: "Times New Roman"; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: rgb(255, 255, 255); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">[ExFMA-2026]
Explainability and Fairness in Multimedia Analysis</h3>
<p><a class="moz-txt-link-freetext" href="https://cbmi2026.sciencesconf.org/resource/page/id/18#exfma">https://cbmi2026.sciencesconf.org/resource/page/id/18#exfma</a></p>
<p
style="color: rgb(0, 0, 0); font-family: Roboto, sans-serif; font-size: medium; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: rgb(255, 255, 255); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">Recent
advances in machine learning, and in particular deep learning,
have led to remarkable performance gains in multimedia analysis
tasks. However, it has also raised questions about the
reliability, explicability, and fairness of their predictions for
decision-making (e.g., the black box problem of the deep models
and the risk of biased outcomes). This lack of transparency and
potential unfairness raises many ethical and political concerns
that prevent wider adoption of this potentially highly beneficial
technology, especially when such systems are deployed in
high-stakes or socially sensitive domains.</p>
<p
style="color: rgb(0, 0, 0); font-family: Roboto, sans-serif; font-size: medium; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: rgb(255, 255, 255); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">Most
multimedia applications, such as person detection/tracking, face
recognition, or lifelog analysis, involve sensitive personal
information. This raises both legal issues, such as data
protection and regulations in the ongoing European AI regulation,
as well as ethical concerns related to discrimination, demographic
bias, and potential misuse of these technologies.</p>
<p
style="color: rgb(0, 0, 0); font-family: Roboto, sans-serif; font-size: medium; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: rgb(255, 255, 255); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">These
challenges are particularly acute in multimedia applications,
where models operate on high-dimensional, multimodal data, and
where predictions frequently rely on subtle semantic cues that are
difficult to interpret even for human experts. Biases may emerge
from data imbalance, annotation practices, model design, or
deployment contexts, and may disproportionately affect certain
individuals or communities. It is therefore crucial not only to
understand how predictions correlate with information perception
and expert decision-making but also whether they are equitable
across groups and aligned with societal values. The objective of
eXplainable AI (XAI) and Fair AI is to improve transparency,
mitigate bias, and foster meaningful human</p>
<p
style="color: rgb(0, 0, 0); font-family: Roboto, sans-serif; font-size: medium; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: rgb(255, 255, 255); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">understanding
of AI systems.</p>
<p
style="color: rgb(0, 0, 0); font-family: Roboto, sans-serif; font-size: medium; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: rgb(255, 255, 255); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">This
special session focuses on methods and applications for
explainable and fair multimedia analysis, with an emphasis on
explanations that are faithful to the underlying models,
meaningful to end users, actionable for domain experts, and
supportive of bias detection and mitigation. The goal is to bring
together researchers and practitioners working on theoretical,
methodological, and applied aspects of explainability, fairness,
evaluation, and interaction in multimedia AI systems.</p>
<p
style="color: rgb(0, 0, 0); font-family: Roboto, sans-serif; font-size: medium; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: rgb(255, 255, 255); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">Topics
of interest include (but are not limited to):</p>
<ul
style="color: rgb(0, 0, 0); font-family: "Times New Roman"; font-size: medium; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: rgb(255, 255, 255); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">
<li style="color: rgb(0, 0, 0) !important;">Analysis of the
influencing factors relevant to the final decision as an
essential step to understand and improve the underlying
processes involved.</li>
<li style="color: rgb(0, 0, 0) !important;">Methods for bias
detection, fairness assessment, and mitigation in multimedia
dataset and models.</li>
<li style="color: rgb(0, 0, 0) !important;">Fairness-aware
learning strategies for multimedia analysis.</li>
<li style="color: rgb(0, 0, 0) !important;">Information
visualization for models or their predictions.</li>
<li style="color: rgb(0, 0, 0) !important;">Visual analytics and
Interactive applications for XAI.</li>
<li style="color: rgb(0, 0, 0) !important;">Performance evaluation
metrics and protocols for explainability.</li>
<li style="color: rgb(0, 0, 0) !important;"> Performance
evaluation metrics and protocols for fairness.</li>
<li style="color: rgb(0, 0, 0) !important;">Sample-centric and
dataset-centric explanations, including subgroup analyses</li>
<li style="color: rgb(0, 0, 0) !important;">Attention mechanisms
for XAI.</li>
<li style="color: rgb(0, 0, 0) !important;">XAI-based pruning.</li>
<li style="color: rgb(0, 0, 0) !important;">XAI for multimedia
systems supporting domain experts (e.g., healthcare, security,
cultural heritage).</li>
<li style="color: rgb(0, 0, 0) !important;">Open challenges from
industry or existing and emerging regulatory frameworks.</li>
<li style="color: rgb(0, 0, 0) !important;">Industrial use cases
and deployment challenges.</li>
</ul>
<p
style="color: rgb(0, 0, 0); font-family: Roboto, sans-serif; font-size: medium; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: rgb(255, 255, 255); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">The
special session aims to collect high-quality scientific
contributions that advance the state of the art in explainable and
fair multimedia analysis, and to foster interdisciplinary
discussion on how transparency, fairness, and accountability can
be jointly addressed in multimedia AI systems. By integrating
explainability and fairness, the session seeks to promote
trustworthy AI technologies that enhance societal benefit while
minimizing risks of bias, discrimination, and unintended harm.</p>
<p
style="color: rgb(0, 0, 0); font-family: Roboto, sans-serif; font-size: medium; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: rgb(255, 255, 255); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;"><strong>Important
dates :</strong></p>
<p
style="color: rgb(0, 0, 0); font-family: Roboto, sans-serif; font-size: medium; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: rgb(255, 255, 255); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">Paper
deadline: 20 APRIL 2026 </p>
<p
style="color: rgb(0, 0, 0); font-family: Roboto, sans-serif; font-size: medium; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: rgb(255, 255, 255); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">Notification:
22 MAY 2026</p>
<p
style="color: rgb(0, 0, 0); font-family: Roboto, sans-serif; font-size: medium; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: rgb(255, 255, 255); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">Camera-ready:
15 JUNE 2026</p>
<p
style="color: rgb(0, 0, 0); font-family: Roboto, sans-serif; font-size: medium; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: rgb(255, 255, 255); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">Paper
submission :<span> </span><a
href="https://cbmi2026.sciencesconf.org/resource/page/id/12"
style="color: rgb(102, 102, 102);">Author Guidelines</a></p>
<p
style="color: rgb(0, 0, 0); font-family: Roboto, sans-serif; font-size: medium; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: rgb(255, 255, 255); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">Please
indicate in the comments that this paper is for SS <span> </span><strong>ExFMA-2026</strong></p>
<p
style="color: rgb(0, 0, 0); font-family: Roboto, sans-serif; font-size: medium; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: rgb(255, 255, 255); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;"><strong>SS
chairs</strong></p>
<ul
style="color: rgb(0, 0, 0); font-family: "Times New Roman"; font-size: medium; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: rgb(255, 255, 255); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">
<li style="color: rgb(0, 0, 0) !important;">Chiara Galdi, EURECOM,
Sophia Antipolis, France.</li>
<li class="_mce_tagged_br" style="color: rgb(0, 0, 0) !important;">Romain
Bourqui, Université of Bordeaux</li>
<li class="_mce_tagged_br" style="color: rgb(0, 0, 0) !important;">Martin
Winter, JOANNEUM RESEARCH - DIGITAL, Graz, Austria.</li>
<li class="_mce_tagged_br" style="color: rgb(0, 0, 0) !important;">Romain
Giot, Université of Bordeaux</li>
</ul>
<p></p>
<pre class="moz-signature" cols="72">--
Cordiali saluti / Bien cordialement / Kind regards,
Chiara
--
Chiara GALDI, PhD
Assistant Professor
Dept. of Digital Security
EURECOM Campus SophiaTech
450 Route des Chappes
06410 Biot Sophia Antipolis
FRANCE
<a class="moz-txt-link-abbreviated" href="mailto:galdi@eurecom.fr">galdi@eurecom.fr</a>
Phone : +33 (0)4 93.00.81.67
Fax : +33 (0)4 93.00.82.00
<a class="moz-txt-link-freetext" href="http://www.eurecom.fr/~galdi">http://www.eurecom.fr/~galdi</a></pre>
</body>
</html>