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/ViTPose-B (Single-task_Det-bbox_256x192)

ViTPose-B (Single-task_Det-bbox_256x192)

Reported on 12 benchmarks across 3 tasks · 1 paper · 3 SOTA

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

Computer Vision4 results

Pose EstimationonCOCO val2017
AR· 2022-04-26
81.1
best: 82.2 (MogaNet-B (384x288))
SOTA
ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation arXiv:2204.12484
Pose EstimationonCOCO val2017
AP· 2022-04-26
75.8
best: 78.1 (CCNet (ViTPose-B_GT-bbox_256x192))
ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation arXiv:2204.12484
Pose EstimationonCOCO val2017
AP50· 2022-04-26
90.7
best: 93.7 (CCNet (ViTPose-B_GT-bbox_256x192))
ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation arXiv:2204.12484
Pose EstimationonCOCO val2017
AP75· 2022-04-26
83.2
best: 85 (CCNet (ViTPose-B_GT-bbox_256x192))
ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation arXiv:2204.12484

Methodology4 results

3DonCOCO val2017
AR· 2022-04-26
81.1
best: 82.2 (MogaNet-B (384x288))
SOTA
ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation arXiv:2204.12484
3DonCOCO val2017
AP· 2022-04-26
75.8
best: 78.1 (CCNet (ViTPose-B_GT-bbox_256x192))
ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation arXiv:2204.12484
3DonCOCO val2017
AP50· 2022-04-26
90.7
best: 93.7 (CCNet (ViTPose-B_GT-bbox_256x192))
ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation arXiv:2204.12484
3DonCOCO val2017
AP75· 2022-04-26
83.2
best: 85 (CCNet (ViTPose-B_GT-bbox_256x192))
ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation arXiv:2204.12484

Audio4 results

1 Image, 2*2 StitchionCOCO val2017
AR· 2022-04-26
81.1
best: 82.2 (MogaNet-B (384x288))
SOTA
ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation arXiv:2204.12484
1 Image, 2*2 StitchionCOCO val2017
AP· 2022-04-26
75.8
best: 78.1 (CCNet (ViTPose-B_GT-bbox_256x192))
ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation arXiv:2204.12484
1 Image, 2*2 StitchionCOCO val2017
AP50· 2022-04-26
90.7
best: 93.7 (CCNet (ViTPose-B_GT-bbox_256x192))
ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation arXiv:2204.12484
1 Image, 2*2 StitchionCOCO val2017
AP75· 2022-04-26
83.2
best: 85 (CCNet (ViTPose-B_GT-bbox_256x192))
ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation arXiv:2204.12484