add video description

index.html

@@ -199,10 +199,20 @@ <h2 class="subtitle has-text-centered">
           </video>
         </div>
       </div>
+
+      <div class="content has-text-justified" style="margin-top: 20px;">
+        <p>
+          Videos 1. Test dataset. Synthesized talking head video samples extracted from the test dataset. The labels 320, 640, 1280, and 2560 represent the training epochs of the framework's first stage, which utilizes a Transformer-based model. The second stage model is fixed at the optimal epoch, 120. The label 'original_keypoints' indicates the ground truth landmarks used as input for the second stage framework. The final sample, without a label, is the real video sample.
+        </p>
+      </div>
     </div>
+
+
   </div>
 </section>
 
+
+
 <section class="hero is-light is-small">
   <div class="hero-body">
     <div class="container">
@@ -251,6 +261,12 @@ <h2 class="subtitle has-text-centered">
         </div>
 
       </div>
+
+      <div class="content has-text-justified" style="margin-top: 20px;">
+        <p>
+          Videos 2. Exploration Test. Synthesized talking head video samples extracted from YouTube speech videos.
+        </p>
+      </div>
     </div>
   </div>
 </section>