Update app.py

app.py

@@ -25,12 +25,30 @@ These visual infos are extracted from the video that is usually a short sequence
 
 As a smart assistant, you must understand that Repetitive visual element of the same person or group of subject means that it is the same person/subject, filmed without cut.
 For example, if visual elements is like this: 
-"An older man wearing a brown hat and glasses, looking off into the distance.
- An older man wearing a brown hat and glasses, with a beard and a mustache, is looking directly at the camera.
- An older man wearing a brown hat and glasses, with a beard and a beard on his chin, is looking at the camera."
-It does not mean there are 3 older men, but it means this is the same man. Because we have extracted close frames from the video sequence.
-So with his in mind, what you must understand from this list is actually : 
-"The older man wearing a brown hat and glasses, with a beard is doing some stuff"
+"A man wearing glasses sits on a train and looks out the window.
+A man with glasses and a beard is looking to the right.
+A man is wearing glasses and a beret.
+A man is wearing glasses and a beret.
+A man wearing glasses and a beret is looking to the right.
+A man with glasses and a beard is looking to the left.
+A man with glasses and a beard is looking to the right.
+A man with glasses is wearing a brown jacket.
+A man is wearing glasses and a beret.
+A man with glasses and a beard is looking to the left.
+A man with glasses and a beard is looking to the left."
+
+What you MUST understand from this list is actually : 
+"The man wearing glasses sits on a train and looks out the window.
+The man with glasses and a beard is looking to the right.
+The man is wearing glasses and a beret.
+The man is wearing glasses and a beret.
+The man wearing glasses and a beret is looking to the right.
+The man with glasses and a beard is looking to the left.
+The man with glasses and a beard is looking to the right.
+The man with glasses is wearing a brown jacket.
+The man is wearing glasses and a beret.
+The man with glasses and a beard is looking to the left.
+The man with glasses and a beard is looking to the left."
 
 Audio events are actually the entire scene description based on the audio of the video.