AP: 77.3AP50: 91.4AP75: 84AR: 82.2
Papers with Code · CC BY-SA 4.0
Pose Estimation
Pose Estimation is a computer vision task where the goal is to detect the position and orientation of a person or an object. Usually, this is done by predicting the location of specific keypoints like hands, head, elbows, etc. in case of Human Pose Estimation.
A common benchmark for this task is MPII Human Pose
<span style="color:grey; opacity: 0.6">( Image credit: Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose )</span>
논문
AP: 78.7
AP: 79.5AR: 81.9AP50: 93.6AP75: 85.9
AP: 77.8
AP: 77.3AP50: 93.5AP75: 84.5AR: 80.4
AP: 76.6AR: 81.5
AP: 75.3AP50: -AP75: -AR: -
AP: 79.0
AP: 71.3AP50: 88.9AP75: 78.3AR: -
AP: 77.1
AP: 77.3AR: 82.1AP50: 91AP75: 83.6
Mean PCK@0.2: 97.7
AP: 78.1AP50: 93.7AP75: 85.0AR: 80.4
AP: 72.6AR: 79.4
Mean PCK@0.2: 81.1
AP: 75.8AP50: -AP75: -AR: -
Mean PCK@0.2: 96.5
Mean mAP: 75.5
Mean mAP: 75.5
Mean PCK@0.2: 99.3
Mean mAP: 83.44