config/examples/x2t_video_example.json

{
  "0001": {
    "interleave_array": [
      "assets/video-understanding/videos/video-understanding-caption-long-01.mp4",
      [
        "Describe the key features of the input video, including color, shape, size, texture, objects, background.",
        "Offer a account of the  behavioral process shown in this video.",
        "In a sunlit meadow, a small tortoiseshell butterfly rests on a purple flower. A bee with black and yellow stripes lands on the same flower. The butterfly flaps its wings gently while the bee collects nectar. The flower sways slightly in the breeze. The butterfly then takes off, and the bee follows toward another flower. The video captures a peaceful natural interaction between insects, with vivid colors and a soft meadow background."
      ]
    ],
    "element_dtype_array": [
      "video",
      "text"
    ],
    "istarget_in_interleave": [
      0,
      1
    ]
  },
  "0002": {
    "interleave_array": [
      "assets/video-understanding/videos/video-understanding-caption-short-01.mp4",
      [
        "Describe the key features of the input video, including color, shape, size, texture, objects, background.",
        "Offer a succinct account of the culinary process shown in this video.",
        "A person adds tomato puree to chicken pieces and mixes everything together."
      ]
    ],
    "element_dtype_array": [
      "video",
      "text"
    ],
    "istarget_in_interleave": [
      0,
      1
    ]
  },
  "0003": {
    "interleave_array": [
      "assets/video-understanding/videos/video-understanding-vqa-01.mp4",
      [
        "View the video attentively and provide a suitable answer to the posed question.",
        "How many times did the person launch objects on the table?",
        "3"
      ]
    ],
    "element_dtype_array": [
      "video",
      "text"
    ],
    "istarget_in_interleave": [
      0,
      1
    ]
  }
}