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/MIPNet (gt-bb)

MIPNet (gt-bb)

Reported on 12 benchmarks across 4 tasks · 1 paper · 12 SOTA

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

Computer Vision6 results

  • Pose EstimationonOCHuman
    AP50· 2021-01-27
    89.7
    SOTA
    Multi-Instance Pose Networks: Rethinking Top-Down Pose EstimationarXiv:2101.11223
  • Pose EstimationonOCHuman
    AP75· 2021-01-27
    80.1
    SOTA
    Multi-Instance Pose Networks: Rethinking Top-Down Pose EstimationarXiv:2101.11223
  • Pose EstimationonOCHuman
    Validation AP· 2021-01-27
    74.1
    best: 92.8 (ViTPose (ViTAE-G, GT bounding boxes))
    SOTA
    Multi-Instance Pose Networks: Rethinking Top-Down Pose EstimationarXiv:2101.11223
  • Multi-Person Pose EstimationonOCHuman
    AP50· 2021-01-27
    89.7
    SOTA
    Multi-Instance Pose Networks: Rethinking Top-Down Pose EstimationarXiv:2101.11223
  • Multi-Person Pose EstimationonOCHuman
    AP75· 2021-01-27
    80.1
    SOTA
    Multi-Instance Pose Networks: Rethinking Top-Down Pose EstimationarXiv:2101.11223
  • Multi-Person Pose EstimationonOCHuman
    Validation AP· 2021-01-27
    74.1
    SOTA
    Multi-Instance Pose Networks: Rethinking Top-Down Pose EstimationarXiv:2101.11223

Methodology3 results

  • 3DonOCHuman
    AP50· 2021-01-27
    89.7
    SOTA
    Multi-Instance Pose Networks: Rethinking Top-Down Pose EstimationarXiv:2101.11223
  • 3DonOCHuman
    AP75· 2021-01-27
    80.1
    SOTA
    Multi-Instance Pose Networks: Rethinking Top-Down Pose EstimationarXiv:2101.11223
  • 3DonOCHuman
    Validation AP· 2021-01-27
    74.1
    best: 92.8 (ViTPose (ViTAE-G, GT bounding boxes))
    SOTA
    Multi-Instance Pose Networks: Rethinking Top-Down Pose EstimationarXiv:2101.11223

Audio3 results

  • 1 Image, 2*2 StitchionOCHuman
    AP50· 2021-01-27
    89.7
    SOTA
    Multi-Instance Pose Networks: Rethinking Top-Down Pose EstimationarXiv:2101.11223
  • 1 Image, 2*2 StitchionOCHuman
    AP75· 2021-01-27
    80.1
    SOTA
    Multi-Instance Pose Networks: Rethinking Top-Down Pose EstimationarXiv:2101.11223
  • 1 Image, 2*2 StitchionOCHuman
    Validation AP· 2021-01-27
    74.1
    best: 92.8 (ViTPose (ViTAE-G, GT bounding boxes))
    SOTA
    Multi-Instance Pose Networks: Rethinking Top-Down Pose EstimationarXiv:2101.11223