• smoking
  • clerks
  • tellers
  • concertgoers
  • answering

Nearest Caption in the Training Dataset

a man in a green t - shirt stands at a rail with a woman in a gray t - shirt and a wrist tattoo .

Generated Captions

  • a woman who is talking on a phone while standing next to some people .
  • a woman in white is on the shoulders of a young man .
  • a man standing in a red shirt and looking down at his hands while a woman stands in front of him .
  • a man standing in front of several people looking at a microphone .
  • a man in a red shirt holding a camera and a young asian women .