MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network

Benchmark Model Rank Results
3d-human-pose-estimation-on-mpi-inf-3dhpMotionAGFormer-L (T=81)#2MPJPE: 16.2AUC: 85.3PCK: 98.2
3d-human-pose-estimation-on-mpi-inf-3dhpMotionAGFormer-S (T=81)#5MPJPE: 17.1AUC: 84.5PCK: 98.3
3d-human-pose-estimation-on-mpi-inf-3dhpMotionAGFormer-B (T=81)#8MPJPE: 18.2AUC: 84.2PCK: 98.3
3d-human-pose-estimation-on-mpi-inf-3dhpMotionAGFormer-XS (T=27)#9MPJPE: 19.2AUC: 83.5PCK: 98.2
monocular-3d-human-pose-estimation-on-human3-6m-protocol-1-monocular-ground-truth-2dMotionAGFormer-L#3MPJPE: 17.3
classification-on-full-body-parkinsonsMotionAGFormer#6F1-score (weighted): 0.42
monocular-3d-human-pose-estimation-on-human3-6mMotionAGFormer-L#6Average MPJPE (mm): 38.4Use Video Sequence: YesFrames Needed: 243…
monocular-3d-human-pose-estimation-on-human3-6mMotionAGFormer-B#7Average MPJPE (mm): 38.4Use Video Sequence: YesFrames Needed: 243…
monocular-3d-human-pose-estimation-on-human3-6mMotionAGFormer-S#15Average MPJPE (mm): 42.5Use Video Sequence: YesFrames Needed: 81…
monocular-3d-human-pose-estimation-on-human3-6mMotionAGFormer-XS#22Average MPJPE (mm): 45.1Use Video Sequence: YesFrames Needed: 27…
3d-human-pose-estimation-on-human36mMotionAGFormer-L#71PA-MPJPE: 32.5