AP: 73.0AP50: 91.7AP75: 80.9APL: 78.1
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: 69.7AP50: 90.7AP75: 77.5APL: 75.0
AP: 70.3AP50: 91.2AP75: 77.8APL: 76.8
AP: 77.2
AP: 73.9AP50: 91.7AP75: 82APL: 79.5
AP: 77AP50: 92.7AP75: 84.5APL: 83.1
AP: 75.7AP50: 90.3AP75: 76.3APL: 79.5
AP: 77.4AP50: 92.6AP75: 84.6APL: 83.7
AP: 70.6AP50: 90.8AP75: 78.2APL: 76.1
AP: 74.6AP50: 91.9AP75: 82.1APL: 80.6
AP: 76.8AP50: 92.5AP75: 84.3APL: 82.5
AP: 76.2AP50: 92.7AP75: 83.8APL: 82.3
AP: 78.3AP50: 9AP75: 85.9
AP: 75.7AP50: 92.4AP75: 83.3APL: 81.2
AP: 76.4AP50: 92.6AP75: 83.7APL: 82.6
AP: 74.7AP50: 91.2AP75: 81.9APL: 81.2
AP: 76.1AP50: 93.4AP75: 83.8APL: 81.5
AP: 72.3AP50: 89.2AP75: 79.1APL: 78.6
AP: 73.7AP50: 91.9AP75: 81.1APL: 80
AP: 68.1APL: 70.5APM: 66.8AR: 88.2
AP: 72.2AP50: 90.9AP75: 80.1APL: 78.8
AP: 76.5AP50: 92.7AP75: 84APL: 73.0
AP: 64.9AP50: 85.5AP75: 71.3APL: 70.0
AP: 75AP50: 92.2AP75: 82.3APL: 81.1