A keypoint is one labelled coordinate the model locates, such as a wrist or an eye corner. Collections of keypoints form skeletons and face meshes; their movement over frames is what fitness counters and AR effects read.
Definition
A single tracked landmark — a joint, a facial point, a hand tip. Pose and face models output sets of keypoints that describe shape and motion.
A keypoint is one labelled coordinate the model locates, such as a wrist or an eye corner. Collections of keypoints form skeletons and face meshes; their movement over frames is what fitness counters and AR effects read.
Also known as
landmark