verify / equipe.html
YassmineNouisser
Fix chatbot URL bug + replace placeholder team with real 6 contributors + team photo banner on equipe.html
d0b59f0
Raw
History Blame Contribute Delete
7.51 kB
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>The team β€” Verify</title>
<link rel="preconnect" href="https://fonts.googleapis.com" />
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
<link href="https://fonts.googleapis.com/css2?family=Playfair+Display:wght@400;700;800&family=Inter:wght@400;500;600;700&display=swap" rel="stylesheet" />
<script src="https://cdn.tailwindcss.com"></script>
<link rel="stylesheet" href="assets/css/styles.css?v=32" />
</head>
<body>
<div id="site-header" data-slim="true"></div>
<main class="container-x">
<section class="px-6 pt-12 pb-6 text-center">
<span class="cat-tag tag-fact" style="display:inline-block;font-size:11px;font-weight:700;text-transform:uppercase;letter-spacing:0.8px;padding:3px 10px;border-radius:2px;margin-bottom:16px;">The team</span>
<h1 class="font-serif" style="font-size:54px;line-height:1.05;margin:0 0 12px;">Six people, six modules</h1>
<p class="mx-auto" style="font-size:18px;color:#4a4a4a;max-width:680px;line-height:1.55;">
Verify was built by a team of six 3rd-year AI engineering students at
ESPRIT School of Engineering. Each module is led by a dedicated
specialist; together we combine computer vision, NLP, forensics and
regulatory knowledge into one platform.
</p>
</section>
<!-- Team photo β€” taken on the ESPRIT campus, 2025-2026 -->
<section class="px-6 pb-10" style="max-width:1100px;margin:0 auto;">
<figure style="margin:0;border:1px solid #e5e7eb;background:#fff;box-shadow:0 6px 24px rgba(15,23,42,0.06);">
<div style="position:relative;background:#0b1020;">
<img src="assets/img/team-photo.jpg" alt="The Verify team at ESPRIT" style="display:block;width:100%;height:auto;object-fit:cover;" />
<div style="position:absolute;left:0;right:0;bottom:0;padding:18px 22px;background:linear-gradient(180deg,transparent 0%,rgba(7,12,30,0.72) 65%,rgba(7,12,30,0.92) 100%);color:#fff;">
<div style="font-family:'Playfair Display',serif;font-size:24px;font-weight:700;letter-spacing:-0.01em;">The Verify team β€” ESPRIT 2025-2026</div>
<div style="font-family:'Inter',sans-serif;font-size:13px;font-weight:500;opacity:0.85;margin-top:4px;letter-spacing:0.02em;text-transform:uppercase;">
Class 3IA1 Β· Group FBAIS Β· Tutors: Mme Sonia Mesbah &amp; M. Mustapha Trabelsi
</div>
</div>
</div>
<figcaption style="padding:14px 20px;font-family:'Inter',sans-serif;font-size:13.5px;color:#4a4a4a;line-height:1.6;border-top:1px solid #e5e7eb;">
Yassmine Nouisser Β· Islem Tellili Β· Malek Tirellil Β· Youssef Jouini Β· Rayen Ayat Β· Maryem Ouichka
</figcaption>
</figure>
</section>
<section class="team-grid">
<article class="team-card">
<div class="avatar" style="background:#ffedd5;color:#9a3412;">Y</div>
<h3>Yassmine Nouisser</h3>
<div class="role">Project Lead β€” Cosmetic Ads Fact-Check &amp; Platform Integration</div>
<p>
Owns the cosmetic-ads fact-checking module (Whisper + EasyOCR + a
curated EU-655/2013 knowledge base with 25 patterns, 33 fake claims
and 145 verified ingredients). Coordinates the full Verify platform β€”
frontend, FastAPI backend, the Verify Assistant chatbot, and the
HuggingFace Space deployment.
</p>
</article>
<article class="team-card">
<div class="avatar" style="background:#dbeafe;color:#1e3a8a;">I</div>
<h3>Islem Tellili</h3>
<div class="role">Lead β€” Fake Media Detection (deepfake &amp; AI-generated)</div>
<p>
Trains and validates the ResNet50 ensemble that powers face-deepfake
detection, paired with an MTCNN face detector and a two-stage
AI-image consensus to catch GAN portraits and diffusion-model
generations the deepfake model alone would miss.
</p>
</article>
<article class="team-card">
<div class="avatar" style="background:#fef3c7;color:#78350f;">M</div>
<h3>Malek Tirellil</h3>
<div class="role">Lead β€” Visual Manipulation &amp; Persuasion</div>
<p>
Designs the multi-signal pipeline that scores persuasion in an image:
TrOCR for on-screen text, a DistilRoBERTa classifier fine-tuned for
clickbait, CLIP zero-shot for sensational visual style, and a curated
OCR-driven urgency lexicon in French and English.
</p>
</article>
<article class="team-card">
<div class="avatar" style="background:#ede9fe;color:#5b21b6;">Y</div>
<h3>Youssef Jouini</h3>
<div class="role">Lead β€” Image-Caption Coherence</div>
<p>
Builds the cross-modal coherence pipeline that compares an image (or
a video) with the caption it is published with β€” fusing CLIP ViT-L/14,
YOLOv8m object detection, EasyOCR on-screen text, SAM segmentation
and Whisper audio transcription into a single verdict.
</p>
</article>
<article class="team-card">
<div class="avatar" style="background:#dcfce7;color:#14532d;">R</div>
<h3>Rayen Ayat</h3>
<div class="role">Lead β€” Image Tampering &amp; Photoshop Forensics</div>
<p>
Owns the photo-forensics module. The pipeline runs three classic
model-free techniques β€” Error-Level Analysis, noise residual and
JPEG ghost β€” to localise edits (splicing, inpainting, copy-move) on
the image with no trained classifier in the loop.
</p>
</article>
<article class="team-card">
<div class="avatar" style="background:#fde2e1;color:#9d174d;">M</div>
<h3>Maryem Ouichka</h3>
<div class="role">Cross-Modal Coherence Analysis</div>
<p>
Investigates how the five detection signals agree (or disagree) on
the same media β€” a transverse study that feeds calibration data back
into the coherence and caption-fidelity modules and helps the
newsroom interpret borderline verdicts.
</p>
</article>
</section>
<!-- Mission band -->
<section class="px-6 py-12 my-6 bg-beige" style="border-top:1px solid var(--line);border-bottom:1px solid var(--line);">
<div class="max-w-3xl mx-auto text-center">
<h2 class="font-serif" style="font-size:36px;margin:0 0 16px;">Our mission</h2>
<p style="font-size:17px;color:#4a4a4a;line-height:1.7;">
Provide the public, journalists and Tunisian institutions with an
independent visual verification toolkit, transparent on its methods
and free from any commercial interest in steering its verdicts.
</p>
</div>
</section>
<section class="px-6 py-10 text-center">
<h3 class="font-serif" style="font-size:28px;margin:0 0 8px;">Want to join us?</h3>
<p class="text-gray-600 mb-6">We're hiring an engineer and a fact-checking journalist.</p>
<a href="#" class="btn-outline">View open positions</a>
</section>
</main>
<div id="site-footer"></div>
<script src="assets/js/config.js?v=2"></script> <script src="assets/js/components.js?v=14"></script>
<script src="assets/js/main.js?v=7"></script>
</body>
</html>