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/SMAP

SMAP

Reported on 12 benchmarks across 7 tasks · 1 paper · 1 SOTA

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

Computer Vision11 results

  • 3D Multi-Person Pose EstimationonPanoptic
    Average MPJPE (mm)· uses extra data· 2020-08-26
    61.8
    best: 135.4 (BMP)
    SOTA
    SMAP: Single-Shot Multi-Person Absolute 3D Pose EstimationarXiv:2008.11469
  • 3D Multi-Person Pose Estimation (root-relative)onMuPoTS-3D
    3DPCK· 2020-08-26
    73.5
    best: 89.6 (TDBU_Net)
    SMAP: Single-Shot Multi-Person Absolute 3D Pose EstimationarXiv:2008.11469
  • 3D Human Pose EstimationonPanoptic
    Average MPJPE (mm)· uses extra data· 2020-08-26
    61.8
    best: 135.4 (BMP)
    SMAP: Single-Shot Multi-Person Absolute 3D Pose EstimationarXiv:2008.11469
  • 3D Human Pose EstimationonMuPoTS-3D
    3DPCK· 2020-08-26
    35.4
    best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
    SMAP: Single-Shot Multi-Person Absolute 3D Pose EstimationarXiv:2008.11469
  • 3D Human Pose EstimationonMuPoTS-3D
    3DPCK· 2020-08-26
    73.5
    best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
    SMAP: Single-Shot Multi-Person Absolute 3D Pose EstimationarXiv:2008.11469
  • 3D Multi-Person Pose Estimation (absolute)onMuPoTS-3D
    3DPCK· 2020-08-26
    35.4
    best: 50.9 (POTR-3D)
    SMAP: Single-Shot Multi-Person Absolute 3D Pose EstimationarXiv:2008.11469
  • Pose EstimationonPanoptic
    Average MPJPE (mm)· uses extra data· 2020-08-26
    61.8
    best: 135.4 (BMP)
    SMAP: Single-Shot Multi-Person Absolute 3D Pose EstimationarXiv:2008.11469
  • Pose EstimationonMuPoTS-3D
    3DPCK· 2020-08-26
    35.4
    best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
    SMAP: Single-Shot Multi-Person Absolute 3D Pose EstimationarXiv:2008.11469
  • Pose EstimationonMuPoTS-3D
    3DPCK· 2020-08-26
    73.5
    best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
    SMAP: Single-Shot Multi-Person Absolute 3D Pose EstimationarXiv:2008.11469
  • 3D Multi-Person Pose EstimationonMuPoTS-3D
    3DPCK· 2020-08-26
    35.4
    best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
    SMAP: Single-Shot Multi-Person Absolute 3D Pose EstimationarXiv:2008.11469
  • 3D Multi-Person Pose EstimationonMuPoTS-3D
    3DPCK· 2020-08-26
    73.5
    best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
    SMAP: Single-Shot Multi-Person Absolute 3D Pose EstimationarXiv:2008.11469

Methodology3 results

  • 3DonPanoptic
    Average MPJPE (mm)· uses extra data· 2020-08-26
    61.8
    best: 135.4 (BMP)
    SMAP: Single-Shot Multi-Person Absolute 3D Pose EstimationarXiv:2008.11469
  • 3DonMuPoTS-3D
    3DPCK· 2020-08-26
    35.4
    best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
    SMAP: Single-Shot Multi-Person Absolute 3D Pose EstimationarXiv:2008.11469
  • 3DonMuPoTS-3D
    3DPCK· 2020-08-26
    73.5
    best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
    SMAP: Single-Shot Multi-Person Absolute 3D Pose EstimationarXiv:2008.11469

Audio3 results

  • 1 Image, 2*2 StitchionPanoptic
    Average MPJPE (mm)· uses extra data· 2020-08-26
    61.8
    best: 135.4 (BMP)
    SMAP: Single-Shot Multi-Person Absolute 3D Pose EstimationarXiv:2008.11469
  • 1 Image, 2*2 StitchionMuPoTS-3D
    3DPCK· 2020-08-26
    35.4
    best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
    SMAP: Single-Shot Multi-Person Absolute 3D Pose EstimationarXiv:2008.11469
  • 1 Image, 2*2 StitchionMuPoTS-3D
    3DPCK· 2020-08-26
    73.5
    best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
    SMAP: Single-Shot Multi-Person Absolute 3D Pose EstimationarXiv:2008.11469