updating fonts

index.html

@@ -189,7 +189,7 @@ <h1 class="title is-1 publication-title">
 
       <!-- Common Caption for both videos below them -->
       <div class="video-caption">
-        <h2 class="subtitle has-text-centered">
+        <h2 class="carousel-section-description">
           <strong>Unsupervised keypoints show temporal consistency –</strong>
           Besides the state of the art results in the paper on images, our
           approach also works on videos. We can find keypoints that show
@@ -205,7 +205,7 @@ <h2 class="subtitle has-text-centered">
         <div class="columns is-centered has-text-centered">
           <div class="column is-four-fifths">
             <h2 class="carousel-section-header">Abstract</h2>
-            <div class="content has-text-justified">
+            <div class="carousel-section-description">
               <p>
                 Unsupervised learning of keypoints and landmarks has seen
                 significant progress with the help of modern neural network
@@ -240,7 +240,7 @@ <h2 class="carousel-section-header">Overview</h2>
           alt="Descriptive Text"
           style="width: 100%; height: auto"
         />
-        <h2 class="subtitle has-text-centered">
+        <h2 class="carousel-section-description">
           We pass a randomly initialized text embedding into Stable Diffusion
           and extract the attention maps. We then optimize the text embedding to
           have localized attention maps, by supervising them to become a
@@ -274,7 +274,7 @@ <h2 class="carousel-section-header">Visualizing keypoint discovery</h2>
                 />
               </div>
             </div>
-            <div class="content has-text-justified">
+            <div class="carousel-section-description">
               <p>
                 This interactive slider shows the progression of our training
                 process for a given token on randomly chosen images. Move the