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/PifPaf (single-scale)

PifPaf (single-scale)

Reported on 9 benchmarks across 3 tasks · 1 paper

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

Computer Vision3 results

  • Pose EstimationonCOCO test-dev
    AP· 2019-03-15
    66.4
    best: 81.1 (ViTPose (ViTAE-G, ensemble))
    PifPaf: Composite Fields for Human Pose EstimationarXiv:1903.06593
  • Pose EstimationonCOCO test-dev
    APL· 2019-03-15
    72.1
    best: 86.5 (PoseBH-H)
    PifPaf: Composite Fields for Human Pose EstimationarXiv:1903.06593
  • Pose EstimationonCOCO test-dev
    APM· 2019-03-15
    62.6
    best: 83.8 (4xRSN-50 (ensemble))
    PifPaf: Composite Fields for Human Pose EstimationarXiv:1903.06593

Methodology3 results

  • 3DonCOCO test-dev
    AP· 2019-03-15
    66.4
    best: 81.1 (ViTPose (ViTAE-G, ensemble))
    PifPaf: Composite Fields for Human Pose EstimationarXiv:1903.06593
  • 3DonCOCO test-dev
    APL· 2019-03-15
    72.1
    best: 86.5 (PoseBH-H)
    PifPaf: Composite Fields for Human Pose EstimationarXiv:1903.06593
  • 3DonCOCO test-dev
    APM· 2019-03-15
    62.6
    best: 83.8 (4xRSN-50 (ensemble))
    PifPaf: Composite Fields for Human Pose EstimationarXiv:1903.06593

Audio3 results

  • 1 Image, 2*2 StitchionCOCO test-dev
    AP· 2019-03-15
    66.4
    best: 81.1 (ViTPose (ViTAE-G, ensemble))
    PifPaf: Composite Fields for Human Pose EstimationarXiv:1903.06593
  • 1 Image, 2*2 StitchionCOCO test-dev
    APL· 2019-03-15
    72.1
    best: 86.5 (PoseBH-H)
    PifPaf: Composite Fields for Human Pose EstimationarXiv:1903.06593
  • 1 Image, 2*2 StitchionCOCO test-dev
    APM· 2019-03-15
    62.6
    best: 83.8 (4xRSN-50 (ensemble))
    PifPaf: Composite Fields for Human Pose EstimationarXiv:1903.06593