Update index.html

index.html

@@ -270,7 +270,7 @@ <h3 style="text-align: center;">Global Mode</h3>
 
 							</tr>
 							<tr>
-								<th><div class="caption" style="width: 1080px;text-align: center;line-height: 1.5;color: black;">"Can you describe this video?"
+								<th><div class="caption" style="width: 1080px;text-align: center;line-height: 1.35;color: black;">"Can you describe this video?"
 								</div></th>
 							</tr>
 							<tr>
@@ -288,7 +288,7 @@ <h3 style="text-align: center;">Global Mode</h3>
 								<th><img width="1080px" src="assets/gob.png" /></th>
 							</tr>
 							<tr>
-								<th><div class="caption" style="width: 1080px;text-align: center;line-height: 1.5;color: black;">"Can you tell me what happened in this movie?"
+								<th><div class="caption" style="width: 1080px;text-align: center;line-height: 1.35;color: black;">"Can you tell me what happened in this movie?"
 								</div></th>
 							</tr>
 							<tr>
@@ -307,7 +307,7 @@ <h3 style="text-align: center;">Global Mode</h3>
 								<th><img width="1080px" src="assets/ice.png" /></th>
 							</tr>
 							<tr>
-								<th><div class="caption" style="width: 1080px;text-align: center;line-height: 1.5;color: black;">"What plot does this movie clip include?"
+								<th><div class="caption" style="width: 1080px;text-align: center;line-height: 1.35;color: black;">"What plot does this movie clip include?"
 								</div></th>
 							</tr>
 							<tr>
@@ -326,7 +326,7 @@ <h3 style="text-align: center;">Global Mode</h3>
 								<th><img width="1080px" src="assets/clips.png" /></th>
 							</tr>
 							<tr>
-								<th><div class="caption" style="width: 1080px;text-align: center;line-height: 1.5;color: black;">"Which movie sequence lasts the longest?"
+								<th><div class="caption" style="width: 1080px;text-align: center;line-height: 1.35;color: black;">"Which movie sequence lasts the longest?"
 								</div></th>
 							</tr>
 							<tr>
@@ -363,13 +363,10 @@ <h3 style="text-align: center;">Global Mode</h3>
 		</div>
 	</div>
 
-	<h3 style="text-align: center;">Abstract</h3>
+	<br>
+	<h3 style="text-align: center;">Benchmark: MovieChat-1K<h3>
 		<p style="text-align: justify; display: flex; justify-content: center; max-width: 800px; margin:auto; font-family:Computer Modern Roman; font-size: larger;"> 
-			Recently, integrating video foundation models and large language models to build a video understanding system can overcome the limitations of specific pre-defined vision
-			tasks. Yet, existing systems can only handle videos with very few frames. For long videos, the computation complexity, memory cost, and long-term temporal connection impose
-			additional challenges. Taking advantage of the AtkinsonShiffrin memory model, with tokens in Transformers being employed as the carriers of memory in combination with
-			our specially designed memory mechanism, we propose the MovieChat to overcome these challenges. MovieChat achieves state-of-the-art performance in long video understanding, along with the released MovieChat-1K benchmark with 1K long video and 14K manual annotations for
-			validation of the effectiveness of our method.
+			To better evaluate the performance of MovieChat, we collect a new benchmark for long video understanding tasks, MovieChat-1K, which contains 1K high quality video clips sourced from various movies and TV series with 14K manual annotations.
 		</p>
 
 <br>