config/examples/x2t_image_example.json

{
  "0001": {
    "interleave_array": [
      "assets/image-understanding/cases/image-understanding-case-01.png",
      [
        "Look at the image carefully and answer the question.",
        "Is the largest segment greater than sum of all the other segments?",
        "Yes, the largest segment in the pie chart is the blue one, which is the most populous segment."
      ]
    ],
    "element_dtype_array": [
      "image",
      "text"
    ],
    "istarget_in_interleave": [
      0,
      1
    ]
  },
  "0002": {
    "interleave_array": [
      "assets/image-understanding/cases/image-understanding-case-02.png",
      [
        "Look at the image carefully and answer the question.",
        "What percentage of respondents want better border security?",
        "29%"
      ]
    ],
    "element_dtype_array": [
      "image",
      "text"
    ],
    "istarget_in_interleave": [
      0,
      1
    ]
  },
  "0003": {
    "interleave_array": [
      "assets/image-understanding/cases/image-understanding-case-03.png",
      [
        "Look at the image carefully and answer the question.",
        "What is the license plate number of the car?",
        "The license plate number of the car is BX62 BFY."
      ]
    ],
    "element_dtype_array": [
      "image",
      "text"
    ],
    "istarget_in_interleave": [
      0,
      1
    ]
  },
  "0004": {
    "interleave_array": [
      "assets/image-understanding/cases/image-understanding-case-04.png",
      [
        "Look at the image carefully and answer the question.",
        "According to the data from the proprietary market research, how much amount was spent on the promotional meetings and events during 1998?",
        "According to the data from the proprietary market research, the total amount spent on the promotional meetings and events during 1998 was approximately $1.3 billion."
      ]
    ],
    "element_dtype_array": [
      "image",
      "text"
    ],
    "istarget_in_interleave": [
      0,
      1
    ]
  },
  "0005": {
    "interleave_array": [
      "assets/image-understanding/cases/image-understanding-case-05.png",
      [
        "Look at the image carefully and answer the question.",
        "What is the appearance of the Colosseum in Rome, Italy?",
        "The Colosseum in Rome, Italy is a magnificent ancient amphitheater made of stone and concrete. It is characterized by its large, arched openings and its semi-circular shape. The Colosseum has been partially restored, and its original color has faded, but the architectural details, like the columns and the semi-circular arches, are still visible. The lighting in the image highlights the grandeur and historical significance of the Colosseum, making it stand out against the backdrop of the evening sky."
      ]
    ],
    "element_dtype_array": [
      "image",
      "text"
    ],
    "istarget_in_interleave": [
      0,
      1
    ]
  },
  "0006": {
    "interleave_array": [
      "assets/image-understanding/cases/image-understanding-case-06.png",
      [
        "Look at the image carefully and answer the question.",
        "How does a total solar eclipse look like from Earth?",
        "A total solar eclipse looks like a dark circle with a bright, white outer edge. This is a result of the Earth's rotation and the Earth's shadow, which partially obscures the sun's light. The bright white edge of the eclipse is caused by the sun's high energy and its interaction with the Earth's atmosphere, while the dark part of the eclipse is due to the Earth's shadow and the surrounding air currents. The solar eclipse's shape, with its bright white edge and dark center, is similar to the shape of a full moon or a dark disk. It is a natural phenomenon that occurs in the atmosphere of the Earth and is an important part of the solar system."
      ]
    ],
    "element_dtype_array": [
      "image",
      "text"
    ],
    "istarget_in_interleave": [
      0,
      1
    ]
  }
}