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/MDN

MDN

Reported on 14 benchmarks across 5 tasks · 2 papers · 6 SOTA

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

Computer Vision8 results

3D Human Pose EstimationonHuman3.6M
Average PMPJPE (mm)· 2019-04-11
42.6
best: 44.3 (Li et al.)
SOTA
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
Pose EstimationonHuman3.6M
Average PMPJPE (mm)· 2019-04-11
42.6
best: 44.3 (Li et al.)
SOTA
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
3D Human Pose EstimationonHuman3.6M
Average MPJPE (mm)· 2019-04-11
52.7
best: 131.7 (Rhodin et al.)
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
3D Human Pose EstimationonHuman3.6M
PA-MPJPE· 2019-04-11
42.6
best: 80.7 (SMPLify (dense))
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
3D Human Pose EstimationonHuman3.6M
Average MPJPE (mm)· 2019-04-11
52.7
best: 131.7 (Rhodin et al.)
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
Pose EstimationonHuman3.6M
Average MPJPE (mm)· 2019-04-11
52.7
best: 131.7 (Rhodin et al.)
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
Pose EstimationonHuman3.6M
PA-MPJPE· 2019-04-11
42.6
best: 80.7 (SMPLify (dense))
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
Pose EstimationonHuman3.6M
Average MPJPE (mm)· 2019-04-11
52.7
best: 131.7 (Rhodin et al.)
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547

Methodology4 results

3DonHuman3.6M
Average PMPJPE (mm)· 2019-04-11
42.6
best: 44.3 (Li et al.)
SOTA
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
3DonHuman3.6M
Average MPJPE (mm)· 2019-04-11
52.7
best: 131.7 (Rhodin et al.)
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
3DonHuman3.6M
PA-MPJPE· 2019-04-11
42.6
best: 89.4 (Kinematic-Structure-Preserved Representation)
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
3DonHuman3.6M
Average MPJPE (mm)· 2019-04-11
52.7
best: 131.7 (Rhodin et al.)
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547

Audio4 results

1 Image, 2*2 StitchionHuman3.6M
Average PMPJPE (mm)· 2019-04-11
42.6
best: 44.3 (Li et al.)
SOTA
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
1 Image, 2*2 StitchionHuman3.6M
Average MPJPE (mm)· 2019-04-11
52.7
best: 131.7 (Rhodin et al.)
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
1 Image, 2*2 StitchionHuman3.6M
PA-MPJPE· 2019-04-11
42.6
best: 80.7 (SMPLify (dense))
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
1 Image, 2*2 StitchionHuman3.6M
Average MPJPE (mm)· 2019-04-11
52.7
best: 131.7 (Rhodin et al.)
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547

Natural Language Processing2 results

Question GenerationonVisual Question Generation
BLEU-1· 2018-08-12
36
SOTA
Multimodal Differential Network for Visual Question Generation arXiv:1808.03986
Question GenerationonCOCO Visual Question Answering (VQA) real images 1.0 open ended
BLEU-1· 2018-08-12
65.1
SOTA
Multimodal Differential Network for Visual Question Generation arXiv:1808.03986