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/TCFormer

TCFormer

Reported on 13 benchmarks across 5 tasks · 1 paper · 2 SOTA

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

Knowledge Base5 results

2D Human Pose EstimationonCOCO-WholeBody
WB· uses extra data· 2022-04-19
64.2
best: 70.2 (RTMW-x)
SOTA
Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer arXiv:2204.08680
2D Human Pose EstimationonCOCO-WholeBody
hand· uses extra data· 2022-04-19
61.4
best: 66.4 (RTMW-x)
SOTA
Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer arXiv:2204.08680
2D Human Pose EstimationonCOCO-WholeBody
body· uses extra data· 2022-04-19
71.8
best: 76.9 (PCNet)
Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer arXiv:2204.08680
2D Human Pose EstimationonCOCO-WholeBody
face· uses extra data· 2022-04-19
79
best: 89.7 (PCNet)
Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer arXiv:2204.08680
2D Human Pose EstimationonCOCO-WholeBody
foot· uses extra data· 2022-04-19
74.4
best: 79.8 (ZoomNet (V0.5 data))
Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer arXiv:2204.08680

Computer Vision4 results

3D Human Pose Estimationon3DPW
MPJPE· 2022-04-19
80.6
best: 130 (HMR)
Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer arXiv:2204.08680
3D Human Pose Estimationon3DPW
PA-MPJPE· 2022-04-19
49.3
best: 157 (Simple-baseline)
Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer arXiv:2204.08680
Pose Estimationon3DPW
MPJPE· 2022-04-19
80.6
best: 130 (HMR)
Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer arXiv:2204.08680
Pose Estimationon3DPW
PA-MPJPE· 2022-04-19
49.3
best: 157 (Simple-baseline)
Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer arXiv:2204.08680

Methodology2 results

3Don3DPW
MPJPE· 2022-04-19
80.6
best: 130 (HMR)
Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer arXiv:2204.08680
3Don3DPW
PA-MPJPE· 2022-04-19
49.3
best: 157 (Simple-baseline)
Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer arXiv:2204.08680

Audio2 results

1 Image, 2*2 Stitchion3DPW
MPJPE· 2022-04-19
80.6
best: 130 (HMR)
Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer arXiv:2204.08680
1 Image, 2*2 Stitchion3DPW
PA-MPJPE· 2022-04-19
49.3
best: 157 (Simple-baseline)
Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer arXiv:2204.08680