Table 2 YOLO annotation format.
From: EgoVision a YOLO-ViT hybrid for robust egocentric object recognition
Class Label | X Center | Y Center | Width | Height |
|---|---|---|---|---|
3 | 0.335323 | 0.762954 | 0.445573 | 0.474093 |
3 | 0.743820 | 0.776282 | 0.423453 | 0.432583 |
9 | 0.453089 | 0.705120 | 0.103229 | 0.237833 |
