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>
데이터셋
213개MPII Multi-PersonMPII Multi-PersonPanopticViCoS Towel DatasetYCB-VideoCOCO test-challengeDTTD-MobileHO-3D v3Horse-10LineMODOCHumanSceneEgo3DPWAGORAGlobalEgoMocap Test DatasetITOP front-viewREDS4- 4x upscalingTriMouse-161UDM10 - 4x upscalingAFLWInLocPanopticSurrealUnrealEgo3D Poses in the Wild ChallengeAIST++BEAT2Biwi 3D Audiovisual Corpus of Affective Communication - B3D(AC)^2DREAM-datasetJ-HMDB