Merge pull request #87 from gujiaxi/website

[license] add license reference of TikTokDataset

index.html

@@ -672,18 +672,18 @@ <h2 class="title is-3">Comparison to state-of-the-art methods</h2>
       <div class="content has-text-justified">
         <h3 class="title is-4">Quantitative evaluation</h3>
         <p>
-          Our method achieves better hand generation quality, and more accurately adheres to the reference pose. Note that our method is not trained on the TikTok dataset.
+          Our method achieves better hand generation quality, and more accurately adheres to the reference pose. Note that our method is not trained on <a href="https://www.kaggle.com/datasets/yasaminjafarian/tiktokdataset">TikTokDataset</a>.
         </p>
       </div>
       <div class="columns is-centered">
           <img src="assets/images/experiments/cmp1.jpg" style="max-width: 800px" />
       </div>
       <h2 class="subtitle has-text-centered">
-        Qualitative comparison to the state-of-the-art methods on TikTok test set.
+        Qualitative comparison to the state-of-the-art methods on the test set of <a href="https://www.kaggle.com/datasets/yasaminjafarian/tiktokdataset">TikTokDataset</a>.
       </h2>
       <div class="content has-text-justified">
       <p>
-        We visualize the 106th frame from seq 338 of TikTok dataset and the pixel-wise difference between consecutive frames. MagicPose exhibits abrupt transitions, while Moore and MuseV show instability in texture and text. In contrast, our method demonstrates stable inter-frame differences and better temporal smoothness.
+        We visualize the 106th frame from seq 338 of <a href="https://www.kaggle.com/datasets/yasaminjafarian/tiktokdataset">TikTokDataset</a> and the pixel-wise difference between consecutive frames. MagicPose exhibits abrupt transitions, while Moore and MuseV show instability in texture and text. In contrast, our method demonstrates stable inter-frame differences and better temporal smoothness.
       </p>
       </div>
       <div class="columns is-centered">
@@ -737,7 +737,7 @@ <h3 class="title is-4">User study</h3>
           <img src="assets/images/experiments/userstudy_export.svg" style="max-width: 480px; width: 100%;" />
       </div>
       <h2 class="subtitle has-text-centered">
-        Preference of MimicMotion (ours) over baseline methods on the TikTok dataset test split. Users prefer MimicMotion over other methods.
+        Preference of MimicMotion (ours) over baseline methods on the test split of <a href="https://www.kaggle.com/datasets/yasaminjafarian/tiktokdataset">TikTokDataset</a>. Users prefer MimicMotion over other methods.
       </h2>
 </div>
 </section>
@@ -827,7 +827,7 @@ <h2 class="title">BibTeX</h2>
           <p>
             This page was built using the <a href="https://github.com/eliahuhorwitz/Academic-project-page-template" target="_blank">Academic Project Page Template</a> which was adopted from the <a href="https://nerfies.github.io" target="_blank">Nerfies</a> project page.
             You are free to borrow the of this website, we just ask that you link back to this page in the footer. <br> This website is licensed under a <a rel="license"  href="http://creativecommons.org/licenses/by-sa/4.0/" target="_blank">Creative
-            Commons Attribution-ShareAlike 4.0 International License</a>.
+            Commons Attribution-ShareAlike 4.0 International License</a>. <br> <a href="https://www.kaggle.com/datasets/yasaminjafarian/tiktokdataset/data">TikTokDataset</a> authored by Yasamin Jafarian in “Learning High Fidelity Depths of Dressed Humans by Watching Social Media Dance Videos” is licensed under a <a rel="license" href="https://creativecommons.org/licenses/by-nc/4.0/" target="_blank">Creative Commons Attribution-NonCommercial 4.0 International License</a>.
           </p>
 
         </div>