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/EvoPose2D-L(512x384)

EvoPose2D-L(512x384)

Reported on 6 benchmarks across 3 tasks · 1 paper · 3 SOTA

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

Computer Vision2 results

  • Pose EstimationonCOCO (Common Objects in Context)
    Validation AP· 2020-11-17
    77.5
    best: 82.2 (Sapiens-2B)
    SOTA
    EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight TransferarXiv:2011.08446
  • Pose EstimationonCOCO (Common Objects in Context)
    Test AP· 2020-11-17
    76.8
    best: 78.6 (4xRSN-50(384×288))
    EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight TransferarXiv:2011.08446

Methodology2 results

  • 3DonCOCO (Common Objects in Context)
    Validation AP· 2020-11-17
    77.5
    best: 82.2 (Sapiens-2B)
    SOTA
    EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight TransferarXiv:2011.08446
  • 3DonCOCO (Common Objects in Context)
    Test AP· 2020-11-17
    76.8
    best: 78.6 (4xRSN-50(384×288))
    EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight TransferarXiv:2011.08446

Audio2 results

  • 1 Image, 2*2 StitchionCOCO (Common Objects in Context)
    Validation AP· 2020-11-17
    77.5
    best: 82.2 (Sapiens-2B)
    SOTA
    EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight TransferarXiv:2011.08446
  • 1 Image, 2*2 StitchionCOCO (Common Objects in Context)
    Test AP· 2020-11-17
    76.8
    best: 78.6 (4xRSN-50(384×288))
    EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight TransferarXiv:2011.08446