GroundingToken
Models & Types · AiDotNet.ComputerVision.Segmentation.Common
A grounding token linking a text span to an image region.
Constructors
| Constructor | Summary |
|---|---|
GroundingToken() |
Properties
| Property | Summary |
|---|---|
double Confidence { get; set; } |
Confidence of the grounding. |
double[] BoundingBox { get; set; } |
Bounding box [x1, y1, x2, y2] of the grounded region. |
int EndIndex { get; set; } |
End character index in the full text response. |
int StartIndex { get; set; } |
Start character index in the full text response. |
int? MaskIndex { get; set; } |
Mask index in the output masks tensor (if a mask was generated). |
string Text { get; set; } |
Text span that was grounded. |