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

HRNet

Reported on 238 benchmarks across 19 tasks · 3 papers · 84 SOTA

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

Methodology132 results

  • 3DonDIS-TE4
    E-measure· 2019-08-20
    0.854
    best: 0.944 (MVANet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-TE4
    MAE· 2019-08-20
    0.092
    best: 0.037 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-TE4
    S-Measure· 2019-08-20
    0.792
    best: 0.91 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-TE4
    max F-Measure· 2019-08-20
    0.772
    best: 0.912 (MVANet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-TE4
    weighted F-measure· 2019-08-20
    0.687
    best: 0.867 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-VD
    S-Measure· 2019-08-20
    0.767
    best: 0.917 (BEN_Base+Refiner)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-VD
    max F-Measure· 2019-08-20
    0.726
    best: 0.923 (BEN_Base)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-TE2
    S-Measure· 2019-08-20
    0.784
    best: 0.924 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-TE2
    max F-Measure· 2019-08-20
    0.747
    best: 0.921 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-TE1
    S-Measure· 2019-08-20
    0.742
    best: 0.899 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-TE3
    S-Measure· 2019-08-20
    0.805
    best: 0.928 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-TE3
    max F-Measure· 2019-08-20
    0.784
    best: 0.936 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-TE4
    E-measure· 2019-08-20
    0.854
    best: 0.944 (MVANet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-TE4
    MAE· 2019-08-20
    0.092
    best: 0.037 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-TE4
    S-Measure· 2019-08-20
    0.792
    best: 0.91 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-TE4
    max F-Measure· 2019-08-20
    0.772
    best: 0.912 (MVANet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-TE4
    weighted F-measure· 2019-08-20
    0.687
    best: 0.867 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-VD
    S-Measure· 2019-08-20
    0.767
    best: 0.917 (BEN_Base+Refiner)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-VD
    max F-Measure· 2019-08-20
    0.726
    best: 0.923 (BEN_Base)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-TE2
    S-Measure· 2019-08-20
    0.784
    best: 0.924 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-TE2
    max F-Measure· 2019-08-20
    0.747
    best: 0.921 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-TE1
    S-Measure· 2019-08-20
    0.742
    best: 0.899 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-TE3
    S-Measure· 2019-08-20
    0.805
    best: 0.928 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-TE3
    max F-Measure· 2019-08-20
    0.784
    best: 0.936 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-TE4
    E-measure· 2019-08-20
    0.854
    best: 0.944 (MVANet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-TE4
    MAE· 2019-08-20
    0.092
    best: 0.037 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-TE4
    S-Measure· 2019-08-20
    0.792
    best: 0.91 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-TE4
    max F-Measure· 2019-08-20
    0.772
    best: 0.912 (MVANet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-TE4
    weighted F-measure· 2019-08-20
    0.687
    best: 0.867 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-VD
    S-Measure· 2019-08-20
    0.767
    best: 0.917 (BEN_Base+Refiner)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-VD
    max F-Measure· 2019-08-20
    0.726
    best: 0.923 (BEN_Base)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-TE2
    S-Measure· 2019-08-20
    0.784
    best: 0.924 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-TE2
    max F-Measure· 2019-08-20
    0.747
    best: 0.921 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-TE1
    S-Measure· 2019-08-20
    0.742
    best: 0.899 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-TE3
    S-Measure· 2019-08-20
    0.805
    best: 0.928 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-TE3
    max F-Measure· 2019-08-20
    0.784
    best: 0.936 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononMFN Dataset
    mIOU· 2019-08-20
    51.7
    best: 62.7 (RoadFormer+ (ConvNeXt-L))
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-TE4
    E-measure· 2019-08-20
    0.854
    best: 0.944 (MVANet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-TE4
    MAE· 2019-08-20
    0.092
    best: 0.037 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-TE4
    S-Measure· 2019-08-20
    0.792
    best: 0.91 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-TE4
    max F-Measure· 2019-08-20
    0.772
    best: 0.912 (MVANet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-TE4
    weighted F-measure· 2019-08-20
    0.687
    best: 0.867 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-VD
    S-Measure· 2019-08-20
    0.767
    best: 0.917 (BEN_Base+Refiner)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-VD
    max F-Measure· 2019-08-20
    0.726
    best: 0.923 (BEN_Base)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-TE2
    S-Measure· 2019-08-20
    0.784
    best: 0.924 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-TE2
    max F-Measure· 2019-08-20
    0.747
    best: 0.921 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-TE1
    S-Measure· 2019-08-20
    0.742
    best: 0.899 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-TE3
    S-Measure· 2019-08-20
    0.805
    best: 0.928 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-TE3
    max F-Measure· 2019-08-20
    0.784
    best: 0.936 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonHARPER
    PCK· 2019-02-25
    868
    SOTA
    Deep High-Resolution Representation Learning for Human Pose EstimationarXiv:1902.09212
  • 3DonDIS-TE4
    HCE· 2019-08-20
    3864
    best: 3999 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-VD
    E-measure· 2019-08-20
    0.824
    best: 0.958 (BEN_Base+Refiner)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-VD
    HCE· 2019-08-20
    1560
    best: 1660 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-VD
    MAE· 2019-08-20
    0.095
    best: 0.027 (BEN_Base+Refiner)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-VD
    weighted F-measure· 2019-08-20
    0.641
    best: 0.896 (BEN_Base+Refiner)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-TE2
    E-measure· 2019-08-20
    0.84
    best: 0.947 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-TE2
    HCE· 2019-08-20
    555
    best: 621 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-TE2
    MAE· 2019-08-20
    0.087
    best: 0.028 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-TE2
    weighted F-measure· 2019-08-20
    0.664
    best: 0.885 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-TE1
    E-measure· 2019-08-20
    0.797
    best: 0.927 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-TE1
    HCE· 2019-08-20
    262
    best: 288 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-TE1
    MAE· 2019-08-20
    0.088
    best: 0.031 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-TE1
    max F-Measure· 2019-08-20
    0.668
    best: 0.89 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-TE1
    weighted F-measure· 2019-08-20
    0.579
    best: 0.846 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-TE3
    E-measure· 2019-08-20
    0.869
    best: 0.957 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-TE3
    HCE· 2019-08-20
    1049
    best: 1146 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-TE3
    MAE· 2019-08-20
    0.08
    best: 0.027 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonDIS-TE3
    weighted F-measure· 2019-08-20
    0.7
    best: 0.9 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonCOFW
    NME (inter-ocular)· 2019-08-20
    3.45
    best: 5.07 (Wing (Feng et al., 2018))
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3Don300W
    NME_inter-ocular (%, Challenge)· 2019-08-20
    5.15
    best: 8.2 (ASMNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3Don300W
    NME_inter-ocular (%, Common)· 2019-08-20
    2.87
    best: 5.09 (3DDFA)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3Don300W
    NME_inter-ocular (%, Full)· 2019-08-20
    3.32
    best: 5.63 (3DDFA)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonWFLW
    NME (inter-ocular)· 2019-08-20
    4.6
    best: 11.13 (ESR)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-TE4
    HCE· 2019-08-20
    3864
    best: 3999 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-VD
    E-measure· 2019-08-20
    0.824
    best: 0.958 (BEN_Base+Refiner)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-VD
    HCE· 2019-08-20
    1560
    best: 1660 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-VD
    MAE· 2019-08-20
    0.095
    best: 0.027 (BEN_Base+Refiner)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-VD
    weighted F-measure· 2019-08-20
    0.641
    best: 0.896 (BEN_Base+Refiner)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-TE2
    E-measure· 2019-08-20
    0.84
    best: 0.947 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-TE2
    HCE· 2019-08-20
    555
    best: 621 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-TE2
    MAE· 2019-08-20
    0.087
    best: 0.028 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-TE2
    weighted F-measure· 2019-08-20
    0.664
    best: 0.885 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-TE1
    E-measure· 2019-08-20
    0.797
    best: 0.927 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-TE1
    HCE· 2019-08-20
    262
    best: 288 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-TE1
    MAE· 2019-08-20
    0.088
    best: 0.031 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-TE1
    max F-Measure· 2019-08-20
    0.668
    best: 0.89 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-TE1
    weighted F-measure· 2019-08-20
    0.579
    best: 0.846 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-TE3
    E-measure· 2019-08-20
    0.869
    best: 0.957 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-TE3
    HCE· 2019-08-20
    1049
    best: 1146 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-TE3
    MAE· 2019-08-20
    0.08
    best: 0.027 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonDIS-TE3
    weighted F-measure· 2019-08-20
    0.7
    best: 0.9 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-TE4
    HCE· 2019-08-20
    3864
    best: 3999 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-VD
    E-measure· 2019-08-20
    0.824
    best: 0.958 (BEN_Base+Refiner)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-VD
    HCE· 2019-08-20
    1560
    best: 1660 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-VD
    MAE· 2019-08-20
    0.095
    best: 0.027 (BEN_Base+Refiner)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-VD
    weighted F-measure· 2019-08-20
    0.641
    best: 0.896 (BEN_Base+Refiner)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-TE2
    E-measure· 2019-08-20
    0.84
    best: 0.947 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-TE2
    HCE· 2019-08-20
    555
    best: 621 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-TE2
    MAE· 2019-08-20
    0.087
    best: 0.028 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-TE2
    weighted F-measure· 2019-08-20
    0.664
    best: 0.885 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-TE1
    E-measure· 2019-08-20
    0.797
    best: 0.927 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-TE1
    HCE· 2019-08-20
    262
    best: 288 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-TE1
    MAE· 2019-08-20
    0.088
    best: 0.031 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-TE1
    max F-Measure· 2019-08-20
    0.668
    best: 0.89 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-TE1
    weighted F-measure· 2019-08-20
    0.579
    best: 0.846 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-TE3
    E-measure· 2019-08-20
    0.869
    best: 0.957 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-TE3
    HCE· 2019-08-20
    1049
    best: 1146 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-TE3
    MAE· 2019-08-20
    0.08
    best: 0.027 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononDIS-TE3
    weighted F-measure· 2019-08-20
    0.7
    best: 0.9 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-TE4
    HCE· 2019-08-20
    3864
    best: 3999 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-VD
    E-measure· 2019-08-20
    0.824
    best: 0.958 (BEN_Base+Refiner)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-VD
    HCE· 2019-08-20
    1560
    best: 1660 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-VD
    MAE· 2019-08-20
    0.095
    best: 0.027 (BEN_Base+Refiner)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-VD
    weighted F-measure· 2019-08-20
    0.641
    best: 0.896 (BEN_Base+Refiner)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-TE2
    E-measure· 2019-08-20
    0.84
    best: 0.947 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-TE2
    HCE· 2019-08-20
    555
    best: 621 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-TE2
    MAE· 2019-08-20
    0.087
    best: 0.028 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-TE2
    weighted F-measure· 2019-08-20
    0.664
    best: 0.885 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-TE1
    E-measure· 2019-08-20
    0.797
    best: 0.927 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-TE1
    HCE· 2019-08-20
    262
    best: 288 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-TE1
    MAE· 2019-08-20
    0.088
    best: 0.031 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-TE1
    max F-Measure· 2019-08-20
    0.668
    best: 0.89 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-TE1
    weighted F-measure· 2019-08-20
    0.579
    best: 0.846 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-TE3
    E-measure· 2019-08-20
    0.869
    best: 0.957 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-TE3
    HCE· 2019-08-20
    1049
    best: 1146 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-TE3
    MAE· 2019-08-20
    0.08
    best: 0.027 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konDIS-TE3
    weighted F-measure· 2019-08-20
    0.7
    best: 0.9 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonCOCO test-dev
    AP50· 2019-02-25
    92.5
    best: 95 (ViTPose (ViTAE-G, ensemble))
    Deep High-Resolution Representation Learning for Human Pose EstimationarXiv:1902.09212
  • 3DonCOCO test-dev
    AP75· 2019-02-25
    83.3
    best: 88.2 (ViTPose (ViTAE-G, ensemble))
    Deep High-Resolution Representation Learning for Human Pose EstimationarXiv:1902.09212
  • 3DonCOCO test-dev
    APL· 2019-02-25
    81.5
    best: 86.5 (PoseBH-H)
    Deep High-Resolution Representation Learning for Human Pose EstimationarXiv:1902.09212
  • 3DonCOCO test-dev
    APM· 2019-02-25
    71.9
    best: 83.8 (4xRSN-50 (ensemble))
    Deep High-Resolution Representation Learning for Human Pose EstimationarXiv:1902.09212
  • 3DonCOCO test-dev
    AR· 2019-02-25
    80.5
    best: 88.2 (Simple Pose)
    Deep High-Resolution Representation Learning for Human Pose EstimationarXiv:1902.09212

Computer Vision81 results

  • Image RestorationonARAD-1K
    MRAE· 2020-05-10
    0.3476
    best: 0.3814 (HSCNN+)
    SOTA
    Hierarchical Regression Network for Spectral Reconstruction from RGB ImagesarXiv:2005.04703
  • Object DetectiononDIS-TE4
    E-measure· 2019-08-20
    0.854
    best: 0.944 (MVANet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-TE4
    MAE· 2019-08-20
    0.092
    best: 0.037 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-TE4
    S-Measure· 2019-08-20
    0.792
    best: 0.91 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-TE4
    max F-Measure· 2019-08-20
    0.772
    best: 0.912 (MVANet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-TE4
    weighted F-measure· 2019-08-20
    0.687
    best: 0.867 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-VD
    S-Measure· 2019-08-20
    0.767
    best: 0.917 (BEN_Base+Refiner)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-VD
    max F-Measure· 2019-08-20
    0.726
    best: 0.923 (BEN_Base)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-TE2
    S-Measure· 2019-08-20
    0.784
    best: 0.924 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-TE2
    max F-Measure· 2019-08-20
    0.747
    best: 0.921 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-TE1
    S-Measure· 2019-08-20
    0.742
    best: 0.899 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-TE3
    S-Measure· 2019-08-20
    0.805
    best: 0.928 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-TE3
    max F-Measure· 2019-08-20
    0.784
    best: 0.936 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Instance SegmentationonBDD100K val
    AP· 2019-08-20
    22.5
    best: 23.6 (Mask Transfiner)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-TE4
    E-measure· 2019-08-20
    0.854
    best: 0.944 (MVANet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-TE4
    MAE· 2019-08-20
    0.092
    best: 0.037 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-TE4
    S-Measure· 2019-08-20
    0.792
    best: 0.91 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-TE4
    max F-Measure· 2019-08-20
    0.772
    best: 0.912 (MVANet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-TE4
    weighted F-measure· 2019-08-20
    0.687
    best: 0.867 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-VD
    S-Measure· 2019-08-20
    0.767
    best: 0.917 (BEN_Base+Refiner)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-VD
    max F-Measure· 2019-08-20
    0.726
    best: 0.923 (BEN_Base)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-TE2
    S-Measure· 2019-08-20
    0.784
    best: 0.924 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-TE2
    max F-Measure· 2019-08-20
    0.747
    best: 0.921 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-TE1
    S-Measure· 2019-08-20
    0.742
    best: 0.899 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-TE3
    S-Measure· 2019-08-20
    0.805
    best: 0.928 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-TE3
    max F-Measure· 2019-08-20
    0.784
    best: 0.936 (PDFNet)
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Scene SegmentationonMFN Dataset
    mIOU· 2019-08-20
    51.7
    best: 62.7 (RoadFormer+ (ConvNeXt-L))
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Pose EstimationonHARPER
    PCK· 2019-02-25
    868
    SOTA
    Deep High-Resolution Representation Learning for Human Pose EstimationarXiv:1902.09212
  • Image RestorationonARAD-1K
    PSNR· 2020-05-10
    26.89
    best: 34.32 (MST++)
    Hierarchical Regression Network for Spectral Reconstruction from RGB ImagesarXiv:2005.04703
  • Image RestorationonARAD-1K
    RMSE· 2020-05-10
    0.055
    best: 0.0248 (MST++)
    Hierarchical Regression Network for Spectral Reconstruction from RGB ImagesarXiv:2005.04703
  • Object DetectiononDIS-TE4
    HCE· 2019-08-20
    3864
    best: 3999 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-VD
    E-measure· 2019-08-20
    0.824
    best: 0.958 (BEN_Base+Refiner)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-VD
    HCE· 2019-08-20
    1560
    best: 1660 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-VD
    MAE· 2019-08-20
    0.095
    best: 0.027 (BEN_Base+Refiner)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-VD
    weighted F-measure· 2019-08-20
    0.641
    best: 0.896 (BEN_Base+Refiner)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-TE2
    E-measure· 2019-08-20
    0.84
    best: 0.947 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-TE2
    HCE· 2019-08-20
    555
    best: 621 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-TE2
    MAE· 2019-08-20
    0.087
    best: 0.028 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-TE2
    weighted F-measure· 2019-08-20
    0.664
    best: 0.885 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-TE1
    E-measure· 2019-08-20
    0.797
    best: 0.927 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-TE1
    HCE· 2019-08-20
    262
    best: 288 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-TE1
    MAE· 2019-08-20
    0.088
    best: 0.031 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-TE1
    max F-Measure· 2019-08-20
    0.668
    best: 0.89 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-TE1
    weighted F-measure· 2019-08-20
    0.579
    best: 0.846 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-TE3
    E-measure· 2019-08-20
    0.869
    best: 0.957 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-TE3
    HCE· 2019-08-20
    1049
    best: 1146 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-TE3
    MAE· 2019-08-20
    0.08
    best: 0.027 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononDIS-TE3
    weighted F-measure· 2019-08-20
    0.7
    best: 0.9 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Face ReconstructiononCOFW
    NME (inter-ocular)· 2019-08-20
    3.45
    best: 5.07 (Wing (Feng et al., 2018))
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Face Reconstructionon300W
    NME_inter-ocular (%, Challenge)· 2019-08-20
    5.15
    best: 8.2 (ASMNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Face Reconstructionon300W
    NME_inter-ocular (%, Common)· 2019-08-20
    2.87
    best: 5.09 (3DDFA)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Face Reconstructionon300W
    NME_inter-ocular (%, Full)· 2019-08-20
    3.32
    best: 5.63 (3DDFA)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Face ReconstructiononWFLW
    NME (inter-ocular)· 2019-08-20
    4.6
    best: 11.13 (ESR)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-TE4
    HCE· 2019-08-20
    3864
    best: 3999 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-VD
    E-measure· 2019-08-20
    0.824
    best: 0.958 (BEN_Base+Refiner)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-VD
    HCE· 2019-08-20
    1560
    best: 1660 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-VD
    MAE· 2019-08-20
    0.095
    best: 0.027 (BEN_Base+Refiner)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-VD
    weighted F-measure· 2019-08-20
    0.641
    best: 0.896 (BEN_Base+Refiner)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-TE2
    E-measure· 2019-08-20
    0.84
    best: 0.947 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-TE2
    HCE· 2019-08-20
    555
    best: 621 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-TE2
    MAE· 2019-08-20
    0.087
    best: 0.028 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-TE2
    weighted F-measure· 2019-08-20
    0.664
    best: 0.885 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-TE1
    E-measure· 2019-08-20
    0.797
    best: 0.927 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-TE1
    HCE· 2019-08-20
    262
    best: 288 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-TE1
    MAE· 2019-08-20
    0.088
    best: 0.031 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-TE1
    max F-Measure· 2019-08-20
    0.668
    best: 0.89 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-TE1
    weighted F-measure· 2019-08-20
    0.579
    best: 0.846 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-TE3
    E-measure· 2019-08-20
    0.869
    best: 0.957 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-TE3
    HCE· 2019-08-20
    1049
    best: 1146 (BSV1)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-TE3
    MAE· 2019-08-20
    0.08
    best: 0.027 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • RGB Salient Object DetectiononDIS-TE3
    weighted F-measure· 2019-08-20
    0.7
    best: 0.9 (PDFNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3D Face ReconstructiononCOFW
    NME (inter-ocular)· 2019-08-20
    3.45
    best: 5.07 (Wing (Feng et al., 2018))
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3D Face Reconstructionon300W
    NME_inter-ocular (%, Challenge)· 2019-08-20
    5.15
    best: 8.2 (ASMNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3D Face Reconstructionon300W
    NME_inter-ocular (%, Common)· 2019-08-20
    2.87
    best: 5.09 (3DDFA)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3D Face Reconstructionon300W
    NME_inter-ocular (%, Full)· 2019-08-20
    3.32
    best: 5.63 (3DDFA)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3D Face ReconstructiononWFLW
    NME (inter-ocular)· 2019-08-20
    4.6
    best: 11.13 (ESR)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Pose EstimationonCOCO test-dev
    AP50· 2019-02-25
    92.5
    best: 95 (ViTPose (ViTAE-G, ensemble))
    Deep High-Resolution Representation Learning for Human Pose EstimationarXiv:1902.09212
  • Pose EstimationonCOCO test-dev
    AP75· 2019-02-25
    83.3
    best: 88.2 (ViTPose (ViTAE-G, ensemble))
    Deep High-Resolution Representation Learning for Human Pose EstimationarXiv:1902.09212
  • Pose EstimationonCOCO test-dev
    APL· 2019-02-25
    81.5
    best: 86.5 (PoseBH-H)
    Deep High-Resolution Representation Learning for Human Pose EstimationarXiv:1902.09212
  • Pose EstimationonCOCO test-dev
    APM· 2019-02-25
    71.9
    best: 83.8 (4xRSN-50 (ensemble))
    Deep High-Resolution Representation Learning for Human Pose EstimationarXiv:1902.09212
  • Pose EstimationonCOCO test-dev
    AR· 2019-02-25
    80.5
    best: 88.2 (Simple Pose)
    Deep High-Resolution Representation Learning for Human Pose EstimationarXiv:1902.09212

Audio9 results

  • 10-shot image generationonARAD-1K
    MRAE· 2020-05-10
    0.3476
    best: 0.3814 (HSCNN+)
    SOTA
    Hierarchical Regression Network for Spectral Reconstruction from RGB ImagesarXiv:2005.04703
  • 10-shot image generationonMFN Dataset
    mIOU· 2019-08-20
    51.7
    best: 62.7 (RoadFormer+ (ConvNeXt-L))
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 10-shot image generationonARAD-1K
    PSNR· 2020-05-10
    26.89
    best: 34.32 (MST++)
    Hierarchical Regression Network for Spectral Reconstruction from RGB ImagesarXiv:2005.04703
  • 10-shot image generationonARAD-1K
    RMSE· 2020-05-10
    0.055
    best: 0.0248 (MST++)
    Hierarchical Regression Network for Spectral Reconstruction from RGB ImagesarXiv:2005.04703
  • 1 Image, 2*2 StitchionCOCO test-dev
    AP50· 2019-02-25
    92.5
    best: 95 (ViTPose (ViTAE-G, ensemble))
    Deep High-Resolution Representation Learning for Human Pose EstimationarXiv:1902.09212
  • 1 Image, 2*2 StitchionCOCO test-dev
    AP75· 2019-02-25
    83.3
    best: 88.2 (ViTPose (ViTAE-G, ensemble))
    Deep High-Resolution Representation Learning for Human Pose EstimationarXiv:1902.09212
  • 1 Image, 2*2 StitchionCOCO test-dev
    APL· 2019-02-25
    81.5
    best: 86.5 (PoseBH-H)
    Deep High-Resolution Representation Learning for Human Pose EstimationarXiv:1902.09212
  • 1 Image, 2*2 StitchionCOCO test-dev
    APM· 2019-02-25
    71.9
    best: 83.8 (4xRSN-50 (ensemble))
    Deep High-Resolution Representation Learning for Human Pose EstimationarXiv:1902.09212
  • 1 Image, 2*2 StitchionCOCO test-dev
    AR· 2019-02-25
    80.5
    best: 88.2 (Simple Pose)
    Deep High-Resolution Representation Learning for Human Pose EstimationarXiv:1902.09212

Medical6 results

  • Semantic SegmentationonMFN Dataset
    mIOU· 2019-08-20
    51.7
    best: 62.7 (RoadFormer+ (ConvNeXt-L))
    SOTA
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3D Face ModellingonCOFW
    NME (inter-ocular)· 2019-08-20
    3.45
    best: 5.07 (Wing (Feng et al., 2018))
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3D Face Modellingon300W
    NME_inter-ocular (%, Challenge)· 2019-08-20
    5.15
    best: 8.2 (ASMNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3D Face Modellingon300W
    NME_inter-ocular (%, Common)· 2019-08-20
    2.87
    best: 5.09 (3DDFA)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3D Face Modellingon300W
    NME_inter-ocular (%, Full)· 2019-08-20
    3.32
    best: 5.63 (3DDFA)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3D Face ModellingonWFLW
    NME (inter-ocular)· 2019-08-20
    4.6
    best: 11.13 (ESR)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919

Knowledge Base5 results

  • 2D Human Pose EstimationonCOCO-WholeBody
    WB· uses extra data· 2019-02-25
    43.2
    best: 70.2 (RTMW-x)
    SOTA
    Deep High-Resolution Representation Learning for Human Pose EstimationarXiv:1902.09212
  • 2D Human Pose EstimationonCOCO-WholeBody
    body· uses extra data· 2019-02-25
    65.9
    best: 76.9 (PCNet)
    SOTA
    Deep High-Resolution Representation Learning for Human Pose EstimationarXiv:1902.09212
  • 2D Human Pose EstimationonCOCO-WholeBody
    face· uses extra data· 2019-02-25
    52.3
    best: 89.7 (PCNet)
    SOTA
    Deep High-Resolution Representation Learning for Human Pose EstimationarXiv:1902.09212
  • 2D Human Pose EstimationonCOCO-WholeBody
    foot· uses extra data· 2019-02-25
    31.4
    best: 79.8 (ZoomNet (V0.5 data))
    Deep High-Resolution Representation Learning for Human Pose EstimationarXiv:1902.09212
  • 2D Human Pose EstimationonCOCO-WholeBody
    hand· uses extra data· 2019-02-25
    30
    best: 66.4 (RTMW-x)
    Deep High-Resolution Representation Learning for Human Pose EstimationarXiv:1902.09212

Music5 results

  • Facial Recognition and ModellingonCOFW
    NME (inter-ocular)· 2019-08-20
    3.45
    best: 5.07 (Wing (Feng et al., 2018))
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Facial Recognition and Modellingon300W
    NME_inter-ocular (%, Challenge)· 2019-08-20
    5.15
    best: 8.2 (ASMNet)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Facial Recognition and Modellingon300W
    NME_inter-ocular (%, Common)· 2019-08-20
    2.87
    best: 5.09 (3DDFA)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Facial Recognition and Modellingon300W
    NME_inter-ocular (%, Full)· 2019-08-20
    3.32
    best: 5.63 (3DDFA)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Facial Recognition and ModellingonWFLW
    NME (inter-ocular)· 2019-08-20
    4.6
    best: 11.13 (ESR)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919