• console
  • presenting
  • tablet
  • bedtime
  • communicating

Nearest Caption in the Training Dataset

four people seated while one holding a remote .

Generated Captions

  • two people are sitting on a couch and one of them is holding a remote control .
  • a couple of a man and a woman on a couch .
  • two people sitting next to each other while holding a remote .
  • a young man and woman are laying on they have a wii remote together .
  • a smiling woman is taking a picture of a young couple looking up .