Deployed 2536c93 with MkDocs version: 1.6.1

2026-05-03 11:47:30 +08:00
commit 1ff86b66fc
418 changed files with 617336 additions and 0 deletions
@@ -0,0 +1,91 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 700 300" width="700" height="300">
+  <defs>
+    <marker id="arrow-blue" markerWidth="8" markerHeight="6" refX="8" refY="3" orient="auto">
+      <path d="M0,0 L8,3 L0,6 Z" fill="#3498db"/>
+    </marker>
+    <marker id="arrow-red" markerWidth="8" markerHeight="6" refX="8" refY="3" orient="auto">
+      <path d="M0,0 L8,3 L0,6 Z" fill="#e74c3c"/>
+    </marker>
+    <marker id="arrow-green" markerWidth="8" markerHeight="6" refX="8" refY="3" orient="auto">
+      <path d="M0,0 L8,3 L0,6 Z" fill="#27ae60"/>
+    </marker>
+  </defs>
+
+  <!-- Title -->
+  <text x="350" y="24" text-anchor="middle" font-family="Arial, sans-serif" font-size="14" font-weight="bold" fill="#333">Multimodal Learning: Mapping Modalities to a Shared Space</text>
+
+  <!-- Input labels -->
+  <text x="48" y="92" text-anchor="middle" font-family="Arial, sans-serif" font-size="10" fill="#666">Image</text>
+  <text x="48" y="162" text-anchor="middle" font-family="Arial, sans-serif" font-size="10" fill="#666">Text</text>
+  <text x="48" y="232" text-anchor="middle" font-family="Arial, sans-serif" font-size="10" fill="#666">Audio</text>
+
+  <!-- Input icons -->
+  <rect x="28" y="96" width="40" height="30" rx="4" fill="#3498db" fill-opacity="0.15" stroke="#3498db" stroke-width="1"/>
+  <text x="48" y="115" text-anchor="middle" font-family="Arial, sans-serif" font-size="9" fill="#3498db">🖼</text>
+
+  <rect x="28" y="166" width="40" height="30" rx="4" fill="#e74c3c" fill-opacity="0.15" stroke="#e74c3c" stroke-width="1"/>
+  <text x="48" y="185" text-anchor="middle" font-family="Arial, sans-serif" font-size="9" fill="#e74c3c">Abc</text>
+
+  <rect x="28" y="236" width="40" height="30" rx="4" fill="#27ae60" fill-opacity="0.15" stroke="#27ae60" stroke-width="1"/>
+  <text x="48" y="255" text-anchor="middle" font-family="Arial, sans-serif" font-size="9" fill="#27ae60">♫</text>
+
+  <!-- Arrows from inputs to encoders -->
+  <line x1="68" y1="111" x2="108" y2="111" stroke="#3498db" stroke-width="1.5" marker-end="url(#arrow-blue)"/>
+  <line x1="68" y1="181" x2="108" y2="181" stroke="#e74c3c" stroke-width="1.5" marker-end="url(#arrow-red)"/>
+  <line x1="68" y1="251" x2="108" y2="251" stroke="#27ae60" stroke-width="1.5" marker-end="url(#arrow-green)"/>
+
+  <!-- Image Encoder -->
+  <rect x="115" y="82" width="130" height="58" rx="8" fill="#3498db" fill-opacity="0.12" stroke="#3498db" stroke-width="1.5"/>
+  <text x="180" y="107" text-anchor="middle" font-family="Arial, sans-serif" font-size="11" font-weight="bold" fill="#3498db">Image Encoder</text>
+  <text x="180" y="122" text-anchor="middle" font-family="Arial, sans-serif" font-size="9" fill="#666">(ViT / ResNet)</text>
+
+  <!-- Text Encoder -->
+  <rect x="115" y="152" width="130" height="58" rx="8" fill="#e74c3c" fill-opacity="0.12" stroke="#e74c3c" stroke-width="1.5"/>
+  <text x="180" y="177" text-anchor="middle" font-family="Arial, sans-serif" font-size="11" font-weight="bold" fill="#e74c3c">Text Encoder</text>
+  <text x="180" y="192" text-anchor="middle" font-family="Arial, sans-serif" font-size="9" fill="#666">(Transformer)</text>
+
+  <!-- Audio Encoder -->
+  <rect x="115" y="222" width="130" height="58" rx="8" fill="#27ae60" fill-opacity="0.12" stroke="#27ae60" stroke-width="1.5"/>
+  <text x="180" y="247" text-anchor="middle" font-family="Arial, sans-serif" font-size="11" font-weight="bold" fill="#27ae60">Audio Encoder</text>
+  <text x="180" y="262" text-anchor="middle" font-family="Arial, sans-serif" font-size="9" fill="#666">(Wav2Vec)</text>
+
+  <!-- Arrows from encoders to shared space -->
+  <line x1="245" y1="111" x2="380" y2="160" stroke="#3498db" stroke-width="1.5" marker-end="url(#arrow-blue)"/>
+  <line x1="245" y1="181" x2="380" y2="178" stroke="#e74c3c" stroke-width="1.5" marker-end="url(#arrow-red)"/>
+  <line x1="245" y1="251" x2="380" y2="198" stroke="#27ae60" stroke-width="1.5" marker-end="url(#arrow-green)"/>
+
+  <!-- Shared Embedding Space ellipse -->
+  <ellipse cx="480" cy="178" rx="130" ry="80" fill="#9b59b6" fill-opacity="0.08" stroke="#9b59b6" stroke-width="1.5" stroke-dasharray="6,3"/>
+  <text x="480" y="108" text-anchor="middle" font-family="Arial, sans-serif" font-size="11" font-weight="bold" fill="#9b59b6">Shared Embedding Space</text>
+
+  <!-- Clustered paired dots — matched pair 1 -->
+  <circle cx="430" cy="155" r="5" fill="#3498db" opacity="0.8"/>
+  <circle cx="440" cy="150" r="5" fill="#e74c3c" opacity="0.8"/>
+  <circle cx="435" cy="163" r="5" fill="#27ae60" opacity="0.8"/>
+
+  <!-- Matched pair 2 -->
+  <circle cx="510" cy="195" r="5" fill="#3498db" opacity="0.8"/>
+  <circle cx="520" cy="190" r="5" fill="#e74c3c" opacity="0.8"/>
+  <circle cx="515" cy="203" r="5" fill="#27ae60" opacity="0.8"/>
+
+  <!-- Matched pair 3 -->
+  <circle cx="470" cy="220" r="5" fill="#3498db" opacity="0.8"/>
+  <circle cx="480" cy="215" r="5" fill="#e74c3c" opacity="0.8"/>
+
+  <!-- Scattered unmatched dots -->
+  <circle cx="550" cy="145" r="4" fill="#3498db" opacity="0.4"/>
+  <circle cx="420" cy="210" r="4" fill="#e74c3c" opacity="0.4"/>
+  <circle cx="540" cy="220" r="4" fill="#27ae60" opacity="0.4"/>
+
+  <!-- Labels for clusters -->
+  <text x="440" y="138" text-anchor="middle" font-family="Arial, sans-serif" font-size="8" fill="#666">matched</text>
+  <text x="518" y="178" text-anchor="middle" font-family="Arial, sans-serif" font-size="8" fill="#666">matched</text>
+
+  <!-- Legend -->
+  <circle cx="390" cy="282" r="4" fill="#3498db"/>
+  <text x="398" y="285" font-family="Arial, sans-serif" font-size="9" fill="#666">Image</text>
+  <circle cx="440" cy="282" r="4" fill="#e74c3c"/>
+  <text x="448" y="285" font-family="Arial, sans-serif" font-size="9" fill="#666">Text</text>
+  <circle cx="485" cy="282" r="4" fill="#27ae60"/>
+  <text x="493" y="285" font-family="Arial, sans-serif" font-size="9" fill="#666">Audio</text>
+</svg>