Liftformer (n=243 CPN)

Reported on 4 benchmarks across 4 tasks · 1 paper

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

Computer Vision2 results

Pose EstimationonHuman3.6M
Average MPJPE (mm)· 2020-09-01
44.8
best: 131.7 (Rhodin et al.)
LiftFormer: 3D Human Pose Estimation using attention models arXiv:2009.00348
3D Pose EstimationonHuman3.6M
Average MPJPE (mm)· 2020-09-01
44.8
best: 48.6 (Liftformer (n=27 CPN))
LiftFormer: 3D Human Pose Estimation using attention models arXiv:2009.00348

Methodology1 result

3DonHuman3.6M
Average MPJPE (mm)· 2020-09-01
44.8
best: 131.7 (Rhodin et al.)
LiftFormer: 3D Human Pose Estimation using attention models arXiv:2009.00348

Audio1 result

1 Image, 2*2 StitchionHuman3.6M
Average MPJPE (mm)· 2020-09-01
44.8
best: 131.7 (Rhodin et al.)
LiftFormer: 3D Human Pose Estimation using attention models arXiv:2009.00348