Bounding Boxes (visual_grounding)

8 objects detected — coordinates are 0-1000 normalized
raccoon
raccoon
coffee cup
banana peel
newspaper
trash can lid
raccoon's face
left eye
right eye
raccoon
[270,240,892,845] • 622×605
coffee cup
[424,115,610,273] • 186×158
banana peel
[472,215,667,291] • 195×76
newspaper
[305,223,548,315] • 243×92
trash can lid
[107,800,1000,998] • 893×198
raccoon's face
[305,283,750,537] • 445×254
left eye
[565,379,605,416] • 40×37
right eye
[442,379,489,413] • 47×34