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/HRNet-W48plus

HRNet-W48plus

Reported on 8 benchmarks across 4 tasks · 1 paper · 5 SOTA

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

Computer Vision4 results

  • Pose EstimationonCOCO minival
    AP· 2020-08-17
    79.1
    SOTA
    AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping AugmentationarXiv:2008.07139
  • Multi-Person Pose EstimationonCOCO test-dev
    AP· 2020-08-17
    78.7
    best: 79.2 (SCIO (HRNet-48))
    SOTA
    AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping AugmentationarXiv:2008.07139
  • Multi-Person Pose EstimationonCOCO minival
    AP· 2020-08-17
    79.1
    SOTA
    AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping AugmentationarXiv:2008.07139
  • Pose EstimationonCOCO test-dev
    AP· 2020-08-17
    78.7
    best: 81.1 (ViTPose (ViTAE-G, ensemble))
    AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping AugmentationarXiv:2008.07139

Methodology2 results

  • 3DonCOCO minival
    AP· 2020-08-17
    79.1
    SOTA
    AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping AugmentationarXiv:2008.07139
  • 3DonCOCO test-dev
    AP· 2020-08-17
    78.7
    best: 81.1 (ViTPose (ViTAE-G, ensemble))
    AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping AugmentationarXiv:2008.07139

Audio2 results

  • 1 Image, 2*2 StitchionCOCO minival
    AP· 2020-08-17
    79.1
    SOTA
    AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping AugmentationarXiv:2008.07139
  • 1 Image, 2*2 StitchionCOCO test-dev
    AP· 2020-08-17
    78.7
    best: 81.1 (ViTPose (ViTAE-G, ensemble))
    AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping AugmentationarXiv:2008.07139