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/GeoRep (fully-supervised)

GeoRep (fully-supervised)

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 EstimationonMPI-INF-3DHP
    MPJPE· 2020-03-17
    110.8
    best: 124.7 (VNect (Augm.))
    Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the WildarXiv:2003.07581
  • 3D Human Pose EstimationonMPI-INF-3DHP
    PCK· 2020-03-17
    80.2
    best: 99.37 (LMT R152 384x384)
    Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the WildarXiv:2003.07581
  • Pose EstimationonMPI-INF-3DHP
    MPJPE· 2020-03-17
    110.8
    best: 124.7 (VNect (Augm.))
    Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the WildarXiv:2003.07581
  • Pose EstimationonMPI-INF-3DHP
    PCK· 2020-03-17
    80.2
    best: 99.37 (LMT R152 384x384)
    Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the WildarXiv:2003.07581

Methodology2 results

  • 3DonMPI-INF-3DHP
    MPJPE· 2020-03-17
    110.8
    best: 124.7 (VNect (Augm.))
    Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the WildarXiv:2003.07581
  • 3DonMPI-INF-3DHP
    PCK· 2020-03-17
    80.2
    best: 99.37 (LMT R152 384x384)
    Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the WildarXiv:2003.07581

Audio2 results

  • 1 Image, 2*2 StitchionMPI-INF-3DHP
    MPJPE· 2020-03-17
    110.8
    best: 124.7 (VNect (Augm.))
    Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the WildarXiv:2003.07581
  • 1 Image, 2*2 StitchionMPI-INF-3DHP
    PCK· 2020-03-17
    80.2
    best: 99.37 (LMT R152 384x384)
    Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the WildarXiv:2003.07581