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/HigherHRNet (ScaleNet_P4)

HigherHRNet (ScaleNet_P4)

Reported on 32 benchmarks across 4 tasks · 1 paper · 9 SOTA

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

Computer Vision16 results

  • Pose EstimationonCrowdPose
    mAP @0.5:0.95· uses extra data· 2020-11-30
    71.3
    best: 83.8 (RTMO-l)
    SOTA
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • Multi-Person Pose EstimationonCOCO test-dev
    AP50· 2020-11-30
    90.3
    best: 93.5 (SCIO (HRNet-48))
    SOTA
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • Multi-Person Pose EstimationonCOCO test-dev
    AP75· 2020-11-30
    78.2
    best: 85.8 (SCIO (HRNet-48))
    SOTA
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • Multi-Person Pose EstimationonCOCO test-dev
    APM· 2020-11-30
    67.5
    best: 74.1 (SCIO (HRNet-48))
    SOTA
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • Multi-Person Pose EstimationonCOCO test-dev
    AR· 2020-11-30
    76
    best: 81.6 (SCIO (HRNet-48))
    SOTA
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • Multi-Person Pose EstimationonCOCO test-dev
    AR50· 2020-11-30
    92.3
    SOTA
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • Multi-Person Pose EstimationonCrowdPose
    mAP @0.5:0.95· uses extra data· 2020-11-30
    71.3
    best: 83.8 (RTMO-l)
    SOTA
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • Pose EstimationonCOCO test-dev
    AP· 2020-11-30
    71.6
    best: 81.1 (ViTPose (ViTAE-G, ensemble))
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • Pose EstimationonCOCO test-dev
    AP50· 2020-11-30
    90.3
    best: 95 (ViTPose (ViTAE-G, ensemble))
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • Pose EstimationonCOCO test-dev
    AP75· 2020-11-30
    78.2
    best: 88.2 (ViTPose (ViTAE-G, ensemble))
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • Pose EstimationonCOCO test-dev
    APL· 2020-11-30
    77.2
    best: 86.5 (PoseBH-H)
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • Pose EstimationonCOCO test-dev
    APM· 2020-11-30
    67.5
    best: 83.8 (4xRSN-50 (ensemble))
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • Pose EstimationonCOCO test-dev
    AR· 2020-11-30
    76
    best: 88.2 (Simple Pose)
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • Pose EstimationonCOCO test-dev
    AR50· 2020-11-30
    92.3
    best: 96.3 (MSPN)
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • Multi-Person Pose EstimationonCOCO test-dev
    AP· 2020-11-30
    71.6
    best: 79.2 (SCIO (HRNet-48))
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • Multi-Person Pose EstimationonCOCO test-dev
    APL· 2020-11-30
    77.2
    best: 84.2 (SCIO (HRNet-48))
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584

Methodology8 results

  • 3DonCrowdPose
    mAP @0.5:0.95· uses extra data· 2020-11-30
    71.3
    best: 83.8 (RTMO-l)
    SOTA
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • 3DonCOCO test-dev
    AP· 2020-11-30
    71.6
    best: 81.1 (ViTPose (ViTAE-G, ensemble))
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • 3DonCOCO test-dev
    AP50· 2020-11-30
    90.3
    best: 95 (ViTPose (ViTAE-G, ensemble))
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • 3DonCOCO test-dev
    AP75· 2020-11-30
    78.2
    best: 88.2 (ViTPose (ViTAE-G, ensemble))
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • 3DonCOCO test-dev
    APL· 2020-11-30
    77.2
    best: 86.5 (PoseBH-H)
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • 3DonCOCO test-dev
    APM· 2020-11-30
    67.5
    best: 83.8 (4xRSN-50 (ensemble))
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • 3DonCOCO test-dev
    AR· 2020-11-30
    76
    best: 88.2 (Simple Pose)
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • 3DonCOCO test-dev
    AR50· 2020-11-30
    92.3
    best: 96.3 (MSPN)
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584

Audio8 results

  • 1 Image, 2*2 StitchionCrowdPose
    mAP @0.5:0.95· uses extra data· 2020-11-30
    71.3
    best: 83.8 (RTMO-l)
    SOTA
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • 1 Image, 2*2 StitchionCOCO test-dev
    AP· 2020-11-30
    71.6
    best: 81.1 (ViTPose (ViTAE-G, ensemble))
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • 1 Image, 2*2 StitchionCOCO test-dev
    AP50· 2020-11-30
    90.3
    best: 95 (ViTPose (ViTAE-G, ensemble))
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • 1 Image, 2*2 StitchionCOCO test-dev
    AP75· 2020-11-30
    78.2
    best: 88.2 (ViTPose (ViTAE-G, ensemble))
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • 1 Image, 2*2 StitchionCOCO test-dev
    APL· 2020-11-30
    77.2
    best: 86.5 (PoseBH-H)
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • 1 Image, 2*2 StitchionCOCO test-dev
    APM· 2020-11-30
    67.5
    best: 83.8 (4xRSN-50 (ensemble))
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • 1 Image, 2*2 StitchionCOCO test-dev
    AR· 2020-11-30
    76
    best: 88.2 (Simple Pose)
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584
  • 1 Image, 2*2 StitchionCOCO test-dev
    AR50· 2020-11-30
    92.3
    best: 96.3 (MSPN)
    ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual RecognitionarXiv:2011.14584