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/Spatio-Temporal Network (T=128)

Spatio-Temporal Network (T=128)

Reported on 24 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 Vision16 results

3D Human Pose EstimationonHumanEva-I
Mean Reconstruction Error (mm)· 2020-04-07
13.5
best: 9.2 (GLA-GCN (T=27, GT))
SOTA
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
Pose EstimationonHumanEva-I
Mean Reconstruction Error (mm)· 2020-04-07
13.5
best: 9.2 (GLA-GCN (T=27, GT))
SOTA
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
3D Human Pose EstimationonMPI-INF-3DHP
PCK· 2020-04-07
84.1
best: 99.37 (LMT R152 384x384)
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
3D Human Pose Estimationon3DPW
PA-MPJPE· 2020-04-07
71.8
best: 157 (Simple-baseline)
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
3D Human Pose EstimationonHuman3.6M
Average MPJPE (mm)· 2020-04-07
40.1
best: 131.7 (Rhodin et al.)
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
3D Human Pose EstimationonHuman3.6M
PA-MPJPE· 2020-04-07
30.7
best: 80.7 (SMPLify (dense))
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
3D Human Pose EstimationonHuman3.6M
Average MPJPE (mm)· 2020-04-07
40.1
best: 131.7 (Rhodin et al.)
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
3D Human Pose EstimationonHuman3.6M
Frames Needed· 2020-04-07
128
best: 300 (Sparseness Meets Deepness)
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
3D Human Pose EstimationonHuman3.6M
PA-MPJPE· 2020-04-07
30.7
best: 80.7 (SMPLify (dense))
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
Pose EstimationonMPI-INF-3DHP
PCK· 2020-04-07
84.1
best: 99.37 (LMT R152 384x384)
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
Pose Estimationon3DPW
PA-MPJPE· 2020-04-07
71.8
best: 157 (Simple-baseline)
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
Pose EstimationonHuman3.6M
Average MPJPE (mm)· 2020-04-07
40.1
best: 131.7 (Rhodin et al.)
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
Pose EstimationonHuman3.6M
PA-MPJPE· 2020-04-07
30.7
best: 80.7 (SMPLify (dense))
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
Pose EstimationonHuman3.6M
Average MPJPE (mm)· 2020-04-07
40.1
best: 131.7 (Rhodin et al.)
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
Pose EstimationonHuman3.6M
Frames Needed· 2020-04-07
128
best: 300 (Sparseness Meets Deepness)
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
Pose EstimationonHuman3.6M
PA-MPJPE· 2020-04-07
30.7
best: 80.7 (SMPLify (dense))
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822

Methodology8 results

3DonHumanEva-I
Mean Reconstruction Error (mm)· 2020-04-07
13.5
best: 9.2 (GLA-GCN (T=27, GT))
SOTA
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
3DonMPI-INF-3DHP
PCK· 2020-04-07
84.1
best: 99.37 (LMT R152 384x384)
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
3Don3DPW
PA-MPJPE· 2020-04-07
71.8
best: 157 (Simple-baseline)
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
3DonHuman3.6M
Average MPJPE (mm)· 2020-04-07
40.1
best: 131.7 (Rhodin et al.)
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
3DonHuman3.6M
PA-MPJPE· 2020-04-07
30.7
best: 89.4 (Kinematic-Structure-Preserved Representation)
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
3DonHuman3.6M
Average MPJPE (mm)· 2020-04-07
40.1
best: 131.7 (Rhodin et al.)
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
3DonHuman3.6M
Frames Needed· 2020-04-07
128
best: 300 (Sparseness Meets Deepness)
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
3DonHuman3.6M
PA-MPJPE· 2020-04-07
30.7
best: 89.4 (Kinematic-Structure-Preserved Representation)
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822

Audio8 results

1 Image, 2*2 StitchionHumanEva-I
Mean Reconstruction Error (mm)· 2020-04-07
13.5
best: 9.2 (GLA-GCN (T=27, GT))
SOTA
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
1 Image, 2*2 StitchionMPI-INF-3DHP
PCK· 2020-04-07
84.1
best: 99.37 (LMT R152 384x384)
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
1 Image, 2*2 Stitchion3DPW
PA-MPJPE· 2020-04-07
71.8
best: 157 (Simple-baseline)
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
1 Image, 2*2 StitchionHuman3.6M
Average MPJPE (mm)· 2020-04-07
40.1
best: 131.7 (Rhodin et al.)
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
1 Image, 2*2 StitchionHuman3.6M
PA-MPJPE· 2020-04-07
30.7
best: 80.7 (SMPLify (dense))
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
1 Image, 2*2 StitchionHuman3.6M
Average MPJPE (mm)· 2020-04-07
40.1
best: 131.7 (Rhodin et al.)
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
1 Image, 2*2 StitchionHuman3.6M
Frames Needed· 2020-04-07
128
best: 300 (Sparseness Meets Deepness)
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822
1 Image, 2*2 StitchionHuman3.6M
PA-MPJPE· 2020-04-07
30.7
best: 80.7 (SMPLify (dense))
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training arXiv:2004.11822