ニューヨーク・タイムズに載った NIC#

Neural Image Captioning

https://www.nytimes.com/2014/11/18/science/researchers-announce-breakthrough-in-content-recognition-software.html

Human: “A group of men playing Frisbee in the park.” Computer model: “A group of young people playing a game of Frisbee.”

  • Human: “A group of men playing Frisbee in the park.”
  • Computer model: “A group of young people playing a game of Frisbee.”

Human: “A young hockey player playing in the ice rink.” Computer model: “Two hockey players are fighting over the puck.”

  • Human: “A young hockey player playing in the ice rink.”
  • Computer model: “Two hockey players are fighting over the puck.”

Human: “A green monster kite soaring in a sunny sky.” Computer model: “A man flying through the air while riding a snowboard.”

  • Human: “A green monster kite soaring in a sunny sky.”
  • Computer model: “A man flying through the air while riding a snowboard.”

Human: “A person riding a dirt bike is covered in mud.” Computer model: “A person riding a motorcycle on a dirt road.”

  • Human: “A person riding a dirt bike is covered in mud.”
  • Computer model: “A person riding a motorcycle on a dirt road.”

Human: “Three different types of pizza on top of a stove.” Computer model: “A pizza sitting on top of a pan on top of a stove.”

  • Human: “Three different types of pizza on top of a stove.”
  • Computer model: “A pizza sitting on top of a pan on top of a stove.”

Human: “Elephants of mixed ages standing in a muddy landscape.” Model: “A herd of elephants walking across a dry grass field.”

  • Human: “Elephants of mixed ages standing in a muddy landscape.”
  • Model: “A herd of elephants walking across a dry grass field.”