Update index.html

index.html

@@ -175,23 +175,23 @@ <h1 class="title is-2 publication-title">
           </h1>
           <div class="is-size-5 publication-authors">
             <div class="author-block">
-              Qinchen Wu,<sup>1</sup></div>
+              Qinchen Wu<sup>1</sup>,</div>
             <div class="author-block">
-              Difei Gao,<sup>1</sup></div>
+              Difei Gao<sup>1</sup>,</div>
             <div class="author-block">
-              Kevin Qinghong Lin,<sup>1</sup></div>
+              Kevin Qinghong Lin<sup>1</sup>,</div>
             <div class="author-block">
               Zhuoyu Wu<sup>2</sup>,
               </div>
             <br>
             <div class="author-block">
-              Xiangwu Guo,<sup>1</sup></div>
+              Xiangwu Guo<sup>1</sup>,</div>
             <div class="author-block">
-              Peiran Li,<sup>1</sup></div>
+              Peiran Li<sup>1</sup>,</div>
             <div class="author-block">
-              Weichen Zhang,<sup>1</sup></div>
+              Weichen Zhang<sup>1</sup>,</div>
             <div class="author-block">
-              Hengxu Wang,<sup>1</sup></div>
+              Hengxu Wang<sup>1</sup>,</div>
             <div class="author-block">
              Mike Zheng Shou<sup>1</sup>
             </div>
@@ -334,7 +334,7 @@ <h2 class="title is-3">Main contributions</h2>
             <p>
               Our work places emphasis on the following three aspects 
             <ul>
-              <li><strong>Dataset:</strong> Act2Cap contains 4K+ GUI video (Action frames), caption pairs collected from automatic pipeline and human demonstration. </li>
+              <li><strong>Dataset:</strong> Act2Cap contains 4K+ GUI video (Action frames), caption pairs collected from GUI layouts including WORD, EXCEL, PPT, AE, PR, WEB through automatic pipeline and human demonstration. </li>
               <li><strong>Benchmark:</strong> Metric for evaluating the quality of narration generated from LLMs. </li>
               <li><strong>Model baseline:</strong> Two stage model effectively designed for narrating actions in GUI. </li>
 <!--               <li><strong>Critic:</strong> Assess every previous action to help Actor adjust the following steps.</li> -->