• fingering
  • surgeon
  • undressing
  • skyping
  • doctor

Nearest Caption in the Training Dataset

an older man and woman are holding their controllers .

Generated Captions

  • a man is holding his hand while another woman in the background .
  • there is a man holding a video game and a woman looking at him .
  • a man holds his hands while another woman sits on a video game standing next to him .
  • two men holding a video game controller in their hands .
  • two men wearing uniform and one holding a video game .