TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/ViTPose-G

ViTPose-G

Reported on 15 benchmarks across 3 tasks · 1 paper · 12 SOTA

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

Computer Vision5 results

  • Pose EstimationonCrowdPose
    AP· 2022-04-26
    78.3
    best: 78.5 (BUCTD-W48 (w/cond. input from PETR, and generative sampling))
    SOTA
    ViTPose: Simple Vision Transformer Baselines for Human Pose EstimationarXiv:2204.12484
  • Pose EstimationonCrowdPose
    AP Hard· 2022-04-26
    67.9
    best: 466 (DETRPose-N)
    SOTA
    ViTPose: Simple Vision Transformer Baselines for Human Pose EstimationarXiv:2204.12484
  • Pose EstimationonCrowdPose
    AP75· 2022-04-26
    81.4
    SOTA
    ViTPose: Simple Vision Transformer Baselines for Human Pose EstimationarXiv:2204.12484
  • Pose EstimationonCrowdPose
    APM· 2022-04-26
    86.6
    SOTA
    ViTPose: Simple Vision Transformer Baselines for Human Pose EstimationarXiv:2204.12484
  • Pose EstimationonCrowdPose
    AP50· 2022-04-26
    85.3
    best: 89.4 (KAPAO-L)
    ViTPose: Simple Vision Transformer Baselines for Human Pose EstimationarXiv:2204.12484

Methodology5 results

  • 3DonCrowdPose
    AP· 2022-04-26
    78.3
    best: 78.5 (BUCTD-W48 (w/cond. input from PETR, and generative sampling))
    SOTA
    ViTPose: Simple Vision Transformer Baselines for Human Pose EstimationarXiv:2204.12484
  • 3DonCrowdPose
    AP Hard· 2022-04-26
    67.9
    best: 466 (DETRPose-N)
    SOTA
    ViTPose: Simple Vision Transformer Baselines for Human Pose EstimationarXiv:2204.12484
  • 3DonCrowdPose
    AP75· 2022-04-26
    81.4
    SOTA
    ViTPose: Simple Vision Transformer Baselines for Human Pose EstimationarXiv:2204.12484
  • 3DonCrowdPose
    APM· 2022-04-26
    86.6
    SOTA
    ViTPose: Simple Vision Transformer Baselines for Human Pose EstimationarXiv:2204.12484
  • 3DonCrowdPose
    AP50· 2022-04-26
    85.3
    best: 89.4 (KAPAO-L)
    ViTPose: Simple Vision Transformer Baselines for Human Pose EstimationarXiv:2204.12484

Audio5 results

  • 1 Image, 2*2 StitchionCrowdPose
    AP· 2022-04-26
    78.3
    best: 78.5 (BUCTD-W48 (w/cond. input from PETR, and generative sampling))
    SOTA
    ViTPose: Simple Vision Transformer Baselines for Human Pose EstimationarXiv:2204.12484
  • 1 Image, 2*2 StitchionCrowdPose
    AP Hard· 2022-04-26
    67.9
    best: 466 (DETRPose-N)
    SOTA
    ViTPose: Simple Vision Transformer Baselines for Human Pose EstimationarXiv:2204.12484
  • 1 Image, 2*2 StitchionCrowdPose
    AP75· 2022-04-26
    81.4
    SOTA
    ViTPose: Simple Vision Transformer Baselines for Human Pose EstimationarXiv:2204.12484
  • 1 Image, 2*2 StitchionCrowdPose
    APM· 2022-04-26
    86.6
    SOTA
    ViTPose: Simple Vision Transformer Baselines for Human Pose EstimationarXiv:2204.12484
  • 1 Image, 2*2 StitchionCrowdPose
    AP50· 2022-04-26
    85.3
    best: 89.4 (KAPAO-L)
    ViTPose: Simple Vision Transformer Baselines for Human Pose EstimationarXiv:2204.12484