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/Projected-pose belief maps + 2D fusion layers

Projected-pose belief maps + 2D fusion layers

Reported on 8 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 Vision4 results

  • 3D Human Pose EstimationonHuman3.6M
    Average MPJPE (mm)· 2017-01-01
    88.39
    best: 131.7 (Rhodin et al.)
    Lifting from the Deep: Convolutional 3D Pose Estimation from a Single ImagearXiv:1701.00295
  • 3D Human Pose EstimationonHuman3.6M
    Frames Needed· 2017-01-01
    1
    best: 300 (Sparseness Meets Deepness)
    Lifting from the Deep: Convolutional 3D Pose Estimation from a Single ImagearXiv:1701.00295
  • Pose EstimationonHuman3.6M
    Average MPJPE (mm)· 2017-01-01
    88.39
    best: 131.7 (Rhodin et al.)
    Lifting from the Deep: Convolutional 3D Pose Estimation from a Single ImagearXiv:1701.00295
  • Pose EstimationonHuman3.6M
    Frames Needed· 2017-01-01
    1
    best: 300 (Sparseness Meets Deepness)
    Lifting from the Deep: Convolutional 3D Pose Estimation from a Single ImagearXiv:1701.00295

Methodology2 results

  • 3DonHuman3.6M
    Average MPJPE (mm)· 2017-01-01
    88.39
    best: 131.7 (Rhodin et al.)
    Lifting from the Deep: Convolutional 3D Pose Estimation from a Single ImagearXiv:1701.00295
  • 3DonHuman3.6M
    Frames Needed· 2017-01-01
    1
    best: 300 (Sparseness Meets Deepness)
    Lifting from the Deep: Convolutional 3D Pose Estimation from a Single ImagearXiv:1701.00295

Audio2 results

  • 1 Image, 2*2 StitchionHuman3.6M
    Average MPJPE (mm)· 2017-01-01
    88.39
    best: 131.7 (Rhodin et al.)
    Lifting from the Deep: Convolutional 3D Pose Estimation from a Single ImagearXiv:1701.00295
  • 1 Image, 2*2 StitchionHuman3.6M
    Frames Needed· 2017-01-01
    1
    best: 300 (Sparseness Meets Deepness)
    Lifting from the Deep: Convolutional 3D Pose Estimation from a Single ImagearXiv:1701.00295