Attention3DHumanPose

Reported on 8 benchmarks across 4 tasks

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision4 results

Methodology2 results

  • 3DonHuman3.6M
    Average MPJPE (mm)
    45.1
    best: 131.7 (Rhodin et al.)
  • 3DonHuman3.6M
    Frames Needed
    243
    best: 300 (Sparseness Meets Deepness)

Audio2 results