Papers with Code · CC BY-SA 4.0

Pose Estimation

3D › Pose Estimation 1,918 평가 기록 213 datasets

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

Mask R-CNN

1703.06870 2017-03-20 이 페이지의 평가 1건
AP: 63.1AP50: 87.3AP75: 68.7APL: 71.4