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/MotionBERT (Finetune)

MotionBERT (Finetune)

Reported on 20 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 Vision10 results

3D Human Pose Estimationon3DPW
MPJPE· 2022-10-12
76.9
best: 130 (HMR)
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
3D Human Pose Estimationon3DPW
MPVPE· 2022-10-12
88.1
best: 119.3 (BMP)
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
3D Human Pose Estimationon3DPW
PA-MPJPE· 2022-10-12
47.2
best: 157 (Simple-baseline)
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
3D Human Pose EstimationonHuman3.6M
Average MPJPE (mm)· uses extra data· 2022-10-12
37.5
best: 131.7 (Rhodin et al.)
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
3D Human Pose EstimationonHuman3.6M
Frames Needed· uses extra data· 2022-10-12
243
best: 300 (Sparseness Meets Deepness)
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
Pose Estimationon3DPW
MPJPE· 2022-10-12
76.9
best: 130 (HMR)
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
Pose Estimationon3DPW
MPVPE· 2022-10-12
88.1
best: 119.3 (BMP)
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
Pose Estimationon3DPW
PA-MPJPE· 2022-10-12
47.2
best: 157 (Simple-baseline)
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
Pose EstimationonHuman3.6M
Average MPJPE (mm)· uses extra data· 2022-10-12
37.5
best: 131.7 (Rhodin et al.)
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
Pose EstimationonHuman3.6M
Frames Needed· uses extra data· 2022-10-12
243
best: 300 (Sparseness Meets Deepness)
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551

Methodology5 results

3Don3DPW
MPJPE· 2022-10-12
76.9
best: 130 (HMR)
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
3Don3DPW
MPVPE· 2022-10-12
88.1
best: 119.3 (BMP)
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
3Don3DPW
PA-MPJPE· 2022-10-12
47.2
best: 157 (Simple-baseline)
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
3DonHuman3.6M
Average MPJPE (mm)· uses extra data· 2022-10-12
37.5
best: 131.7 (Rhodin et al.)
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
3DonHuman3.6M
Frames Needed· uses extra data· 2022-10-12
243
best: 300 (Sparseness Meets Deepness)
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551

Audio5 results

1 Image, 2*2 Stitchion3DPW
MPJPE· 2022-10-12
76.9
best: 130 (HMR)
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
1 Image, 2*2 Stitchion3DPW
MPVPE· 2022-10-12
88.1
best: 119.3 (BMP)
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
1 Image, 2*2 Stitchion3DPW
PA-MPJPE· 2022-10-12
47.2
best: 157 (Simple-baseline)
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
1 Image, 2*2 StitchionHuman3.6M
Average MPJPE (mm)· uses extra data· 2022-10-12
37.5
best: 131.7 (Rhodin et al.)
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
1 Image, 2*2 StitchionHuman3.6M
Frames Needed· uses extra data· 2022-10-12
243
best: 300 (Sparseness Meets Deepness)
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551