{
  "routes": {
    "grounding": [
      "Grounding",
      "Open-vocabulary object localization"
    ],
    "dense": [
      "Dense",
      "Dense instance localization"
    ],
    "referring": [
      "Referring",
      "Language-guided referring"
    ],
    "dense_point": [
      "Dense Point",
      "Dense point prediction"
    ],
    "referring_point_in_mask": [
      "Referring Point in Mask",
      "Point inside a referred target"
    ],
    "dense_point_in_mask": [
      "Dense Point in Mask",
      "Point inside multiple targets"
    ],
    "visual_prompt": [
      "Visual Prompt",
      "Exemplar-guided localization"
    ],
    "ocr": [
      "OCR",
      "Text recognition and localization"
    ],
    "gui": [
      "GUI",
      "Interface element grounding"
    ]
  },
  "help": {
    "grounding": [
      "Open-Vocabulary Grounding",
      "Turn category names into visual primitives: what is present, and where it is.",
      "Separate categories with commas. Select a result to inspect its original pixels.",
      "car, person"
    ],
    "dense": [
      "Grounding in Dense Scenes",
      "Explore object-level perception in crowded scenes, including small and overlapping instances.",
      "Enter object categories. Inspect overlapping predictions one instance at a time.",
      "person, chair"
    ],
    "referring": [
      "Language, Grounded in Context",
      "Link descriptions of appearance, position, and relationships to a specific visual target.",
      "Describe appearance, position, or relationships in a complete phrase.",
      "The person standing beside the table"
    ],
    "dense_point": [
      "Dense Object Pointing",
      "Represent multiple objects as localized points: a compact form of visual grounding.",
      "Describe the targets to locate. Points indicate positions, not object boundaries.",
      "All visible people"
    ],
    "referring_point_in_mask": [
      "Point Inside a Referred Target",
      "Use a description to predict a point inside the target object.",
      "Describe the target. The output is an image-relative point inside the object.",
      "The person wearing a flotation device"
    ],
    "visual_prompt": [
      "Grounding by Visual Example",
      "Use spatial exemplars to identify related instances through a shared grounding interface.",
      "Green INPUT boxes come from your prompt, not model predictions. Coordinates use the 0–999 range.",
      "Given reference boxes <|box_start|><100><100><200><200><|box_end|> ..."
    ],
    "ocr": [
      "Reading with Spatial Context",
      "Bind recognized text to its image region, connecting what is read with where it appears.",
      "Use an OCR instruction. Select a transcription to inspect the original pixels.",
      "Read and locate the text in the image"
    ],
    "dense_point_in_mask": [
      "Point Inside Multiple Targets",
      "Predict an interior point for each matching instance in a crowded scene.",
      "Separate categories with commas. Each prediction marks a point inside an instance.",
      "van, bus, truck, car, pedestrian"
    ],
    "gui": [
      "Grounding Intent in Interfaces",
      "Map an interaction instruction to a visual target within an interface.",
      "Describe the element to select. The demo predicts a point; it does not execute clicks.",
      "Click the search button"
    ]
  },
  "prefixes": {
    "grounding": "Locate all the instances that match the following categories: ",
    "dense": "Locate all the instances that match the following categories: ",
    "referring": "Locate the target referred to by the following description: ",
    "dense_point": "Point to: ",
    "refer_point": "Point to the target referred to by the following description: ",
    "referring_point_in_mask": "Point to the target referred to by the following description: ",
    "dense_point_in_mask": "Point to: ",
    "layout": "Detect all document layout elements that match the following categories: ",
    "gui": "Point to the UI element to click for the following instruction: "
  },
  "categoryRoutes": [
    "dense",
    "dense_point_in_mask",
    "grounding",
    "layout"
  ]
}