Text this: Learning visual saliency based on object's relative relationship

   _____     ___      ____     __   __   _    _   
  / ___//   / _ \\   |  _ \\   \ \\/ // | \  / || 
  \___ \\  / //\ \\  | |_| ||   \ ` //  |  \/  || 
  /    // |  ___  || | .  //     | ||   | .  . || 
 /____//  |_||  |_|| |_|\_\\     |_||   |_|\/|_|| 
`-----`   `-`   `-`  `-` --`     `-`'   `-`  `-`