Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/VideoPose3D (T=243)

VideoPose3D (T=243)

Reported on 16 benchmarks across 4 tasks · 1 paper · 4 SOTA

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

Computer Vision10 results

3D Human Pose EstimationonHuman3.6M
Number of Frames Per View· 2018-11-28
243
SOTA
3D human pose estimation in video with temporal convolutions and semi-supervised training arXiv:1811.11742
Pose EstimationonHuman3.6M
Number of Frames Per View· 2018-11-28
243
SOTA
3D human pose estimation in video with temporal convolutions and semi-supervised training arXiv:1811.11742
3D Human Pose EstimationonHuman3.6M
Average MPJPE (mm)· 2018-11-28
46.8
best: 131.7 (Rhodin et al.)
3D human pose estimation in video with temporal convolutions and semi-supervised training arXiv:1811.11742
3D Human Pose EstimationonHuman3.6M
PA-MPJPE· 2018-11-28
36.5
best: 80.7 (SMPLify (dense))
3D human pose estimation in video with temporal convolutions and semi-supervised training arXiv:1811.11742
3D Human Pose EstimationonHuman3.6M
Average MPJPE (mm)· 2018-11-28
46.8
best: 131.7 (Rhodin et al.)
3D human pose estimation in video with temporal convolutions and semi-supervised training arXiv:1811.11742
3D Human Pose EstimationonHuman3.6M
Frames Needed· 2018-11-28
243
best: 300 (Sparseness Meets Deepness)
3D human pose estimation in video with temporal convolutions and semi-supervised training arXiv:1811.11742
Pose EstimationonHuman3.6M
Average MPJPE (mm)· 2018-11-28
46.8
best: 131.7 (Rhodin et al.)
3D human pose estimation in video with temporal convolutions and semi-supervised training arXiv:1811.11742
Pose EstimationonHuman3.6M
PA-MPJPE· 2018-11-28
36.5
best: 80.7 (SMPLify (dense))
3D human pose estimation in video with temporal convolutions and semi-supervised training arXiv:1811.11742
Pose EstimationonHuman3.6M
Average MPJPE (mm)· 2018-11-28
46.8
best: 131.7 (Rhodin et al.)
3D human pose estimation in video with temporal convolutions and semi-supervised training arXiv:1811.11742
Pose EstimationonHuman3.6M
Frames Needed· 2018-11-28
243
best: 300 (Sparseness Meets Deepness)
3D human pose estimation in video with temporal convolutions and semi-supervised training arXiv:1811.11742

Methodology5 results

3DonHuman3.6M
Number of Frames Per View· 2018-11-28
243
SOTA
3D human pose estimation in video with temporal convolutions and semi-supervised training arXiv:1811.11742
3DonHuman3.6M
Average MPJPE (mm)· 2018-11-28
46.8
best: 131.7 (Rhodin et al.)
3D human pose estimation in video with temporal convolutions and semi-supervised training arXiv:1811.11742
3DonHuman3.6M
PA-MPJPE· 2018-11-28
36.5
best: 89.4 (Kinematic-Structure-Preserved Representation)
3D human pose estimation in video with temporal convolutions and semi-supervised training arXiv:1811.11742
3DonHuman3.6M
Average MPJPE (mm)· 2018-11-28
46.8
best: 131.7 (Rhodin et al.)
3D human pose estimation in video with temporal convolutions and semi-supervised training arXiv:1811.11742
3DonHuman3.6M
Frames Needed· 2018-11-28
243
best: 300 (Sparseness Meets Deepness)
3D human pose estimation in video with temporal convolutions and semi-supervised training arXiv:1811.11742

Audio5 results

1 Image, 2*2 StitchionHuman3.6M
Number of Frames Per View· 2018-11-28
243
SOTA
3D human pose estimation in video with temporal convolutions and semi-supervised training arXiv:1811.11742
1 Image, 2*2 StitchionHuman3.6M
Average MPJPE (mm)· 2018-11-28
46.8
best: 131.7 (Rhodin et al.)
3D human pose estimation in video with temporal convolutions and semi-supervised training arXiv:1811.11742
1 Image, 2*2 StitchionHuman3.6M
PA-MPJPE· 2018-11-28
36.5
best: 80.7 (SMPLify (dense))
3D human pose estimation in video with temporal convolutions and semi-supervised training arXiv:1811.11742
1 Image, 2*2 StitchionHuman3.6M
Average MPJPE (mm)· 2018-11-28
46.8
best: 131.7 (Rhodin et al.)
3D human pose estimation in video with temporal convolutions and semi-supervised training arXiv:1811.11742
1 Image, 2*2 StitchionHuman3.6M
Frames Needed· 2018-11-28
243
best: 300 (Sparseness Meets Deepness)
3D human pose estimation in video with temporal convolutions and semi-supervised training arXiv:1811.11742