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/INT-2 (ResNet-50)

INT-2 (ResNet-50)

Reported on 16 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 Vision8 results

  • 3D Human Pose Estimationon3DPW
    Acceleration Error· 2023-03-01
    16.5
    best: 6.5 (ARTS (Resnet50 L=16))
    Capturing the motion of every joint: 3D human pose and shape estimation with independent tokensarXiv:2303.00298
  • 3D Human Pose Estimationon3DPW
    MPJPE· 2023-03-01
    75.6
    best: 130 (HMR)
    Capturing the motion of every joint: 3D human pose and shape estimation with independent tokensarXiv:2303.00298
  • 3D Human Pose Estimationon3DPW
    MPVPE· 2023-03-01
    87.9
    best: 119.3 (BMP)
    Capturing the motion of every joint: 3D human pose and shape estimation with independent tokensarXiv:2303.00298
  • 3D Human Pose Estimationon3DPW
    PA-MPJPE· 2023-03-01
    42
    best: 157 (Simple-baseline)
    Capturing the motion of every joint: 3D human pose and shape estimation with independent tokensarXiv:2303.00298
  • Pose Estimationon3DPW
    Acceleration Error· 2023-03-01
    16.5
    best: 5.4 (HybridCap)
    Capturing the motion of every joint: 3D human pose and shape estimation with independent tokensarXiv:2303.00298
  • Pose Estimationon3DPW
    MPJPE· 2023-03-01
    75.6
    best: 130 (HMR)
    Capturing the motion of every joint: 3D human pose and shape estimation with independent tokensarXiv:2303.00298
  • Pose Estimationon3DPW
    MPVPE· 2023-03-01
    87.9
    best: 119.3 (BMP)
    Capturing the motion of every joint: 3D human pose and shape estimation with independent tokensarXiv:2303.00298
  • Pose Estimationon3DPW
    PA-MPJPE· 2023-03-01
    42
    best: 157 (Simple-baseline)
    Capturing the motion of every joint: 3D human pose and shape estimation with independent tokensarXiv:2303.00298

Methodology4 results

  • 3Don3DPW
    Acceleration Error· 2023-03-01
    16.5
    best: 5.4 (HybridCap)
    Capturing the motion of every joint: 3D human pose and shape estimation with independent tokensarXiv:2303.00298
  • 3Don3DPW
    MPJPE· 2023-03-01
    75.6
    best: 130 (HMR)
    Capturing the motion of every joint: 3D human pose and shape estimation with independent tokensarXiv:2303.00298
  • 3Don3DPW
    MPVPE· 2023-03-01
    87.9
    best: 119.3 (BMP)
    Capturing the motion of every joint: 3D human pose and shape estimation with independent tokensarXiv:2303.00298
  • 3Don3DPW
    PA-MPJPE· 2023-03-01
    42
    best: 157 (Simple-baseline)
    Capturing the motion of every joint: 3D human pose and shape estimation with independent tokensarXiv:2303.00298

Audio4 results

  • 1 Image, 2*2 Stitchion3DPW
    Acceleration Error· 2023-03-01
    16.5
    best: 5.4 (HybridCap)
    Capturing the motion of every joint: 3D human pose and shape estimation with independent tokensarXiv:2303.00298
  • 1 Image, 2*2 Stitchion3DPW
    MPJPE· 2023-03-01
    75.6
    best: 130 (HMR)
    Capturing the motion of every joint: 3D human pose and shape estimation with independent tokensarXiv:2303.00298
  • 1 Image, 2*2 Stitchion3DPW
    MPVPE· 2023-03-01
    87.9
    best: 119.3 (BMP)
    Capturing the motion of every joint: 3D human pose and shape estimation with independent tokensarXiv:2303.00298
  • 1 Image, 2*2 Stitchion3DPW
    PA-MPJPE· 2023-03-01
    42
    best: 157 (Simple-baseline)
    Capturing the motion of every joint: 3D human pose and shape estimation with independent tokensarXiv:2303.00298