Does the third dimension of the Keypoint Annotations carry any meaning?

Jeff-sjtu / CrowdPose

CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark, CVPR 2019, Oral

310 stars 39 forks source link

Does the third dimension of the Keypoint Annotations carry any meaning? #2

Closed tobiaskalb closed 5 years ago

tobiaskalb commented 5 years ago

In the annotations of the COCO Keypoint dataset the third dimension of the keypoints is a visibility flag v defined as v=0: not labeled (in which case x=y=0), v=1: labeled but not visible, and v=2: labeled and visible.

What is the definition of the third dimension of the keypoints in CrowdPose?

Jeff-sjtu commented 5 years ago

It is a label flag. When v=0, it means the keypoint is not labeled.