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/FaRL-B (epoch 16)

FaRL-B (epoch 16)

Reported on 65 benchmarks across 5 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 Vision26 results

  • Face ReconstructiononAFLW-19
    AUC_box@0.07 (%, Full)· uses extra data· 2021-12-06
    81.3
    best: 81.8 (FiFA)
    SOTA
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3D Face ReconstructiononAFLW-19
    AUC_box@0.07 (%, Full)· uses extra data· 2021-12-06
    81.3
    best: 81.8 (FiFA)
    SOTA
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • Face Reconstructionon300W
    NME_inter-ocular (%, Challenge)· uses extra data· 2021-12-06
    4.45
    best: 8.2 (ASMNet)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • Face Reconstructionon300W
    NME_inter-ocular (%, Common)· uses extra data· 2021-12-06
    2.56
    best: 5.09 (3DDFA)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • Face Reconstructionon300W
    NME_inter-ocular (%, Full)· uses extra data· 2021-12-06
    2.93
    best: 5.63 (3DDFA)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • Face Reconstructionon300W
    NME_inter-pupil (%, Challenge)· uses extra data· 2021-12-06
    6.42
    best: 10.59 (3DDFA)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • Face Reconstructionon300W
    NME_inter-pupil (%, Common)· uses extra data· 2021-12-06
    3.53
    best: 6.15 (3DDFA)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • Face Reconstructionon300W
    NME_inter-pupil (%, Full)· uses extra data· 2021-12-06
    4.11
    best: 7.01 (3DDFA)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • Face ReconstructiononWFW (Extra Data)
    AUC@10 (inter-ocular)· uses extra data· 2021-12-06
    61.16
    best: 63.1 (SH-FAN)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • Face ReconstructiononWFW (Extra Data)
    FR@10 (inter-ocular)· uses extra data· 2021-12-06
    1.76
    best: 3.12 (LUVLi)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • Face ReconstructiononWFW (Extra Data)
    NME (inter-ocular)· uses extra data· 2021-12-06
    3.96
    best: 4.57 (VGG-F)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • Face ReconstructiononAFLW-19
    NME_box (%, Full)· uses extra data· 2021-12-06
    1.334
    best: 4.04 (SAN)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • Face ReconstructiononAFLW-19
    NME_diag (%, Frontal)· uses extra data· 2021-12-06
    0.821
    best: 2.68 (CFSS)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • Face ReconstructiononAFLW-19
    NME_diag (%, Full)· uses extra data· 2021-12-06
    0.943
    best: 3.92 (CFSS)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3D Face ReconstructiononWFW (Extra Data)
    AUC@10 (inter-ocular)· uses extra data· 2021-12-06
    61.16
    best: 63.1 (SH-FAN)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3D Face ReconstructiononWFW (Extra Data)
    FR@10 (inter-ocular)· uses extra data· 2021-12-06
    1.76
    best: 3.12 (LUVLi)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3D Face ReconstructiononWFW (Extra Data)
    NME (inter-ocular)· uses extra data· 2021-12-06
    3.96
    best: 4.57 (VGG-F)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3D Face ReconstructiononAFLW-19
    NME_box (%, Full)· uses extra data· 2021-12-06
    1.334
    best: 4.04 (SAN)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3D Face ReconstructiononAFLW-19
    NME_diag (%, Frontal)· uses extra data· 2021-12-06
    0.821
    best: 2.68 (CFSS)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3D Face ReconstructiononAFLW-19
    NME_diag (%, Full)· uses extra data· 2021-12-06
    0.943
    best: 3.92 (CFSS)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3D Face Reconstructionon300W
    NME_inter-ocular (%, Challenge)· uses extra data· 2021-12-06
    4.45
    best: 8.2 (ASMNet)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3D Face Reconstructionon300W
    NME_inter-ocular (%, Common)· uses extra data· 2021-12-06
    2.56
    best: 5.09 (3DDFA)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3D Face Reconstructionon300W
    NME_inter-ocular (%, Full)· uses extra data· 2021-12-06
    2.93
    best: 5.63 (3DDFA)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3D Face Reconstructionon300W
    NME_inter-pupil (%, Challenge)· uses extra data· 2021-12-06
    6.42
    best: 10.59 (3DDFA)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3D Face Reconstructionon300W
    NME_inter-pupil (%, Common)· uses extra data· 2021-12-06
    3.53
    best: 6.15 (3DDFA)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3D Face Reconstructionon300W
    NME_inter-pupil (%, Full)· uses extra data· 2021-12-06
    4.11
    best: 7.01 (3DDFA)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109

Music13 results

  • Facial Recognition and ModellingonAFLW-19
    AUC_box@0.07 (%, Full)· uses extra data· 2021-12-06
    81.3
    best: 81.8 (FiFA)
    SOTA
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • Facial Recognition and ModellingonWFW (Extra Data)
    AUC@10 (inter-ocular)· uses extra data· 2021-12-06
    61.16
    best: 63.1 (SH-FAN)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • Facial Recognition and ModellingonWFW (Extra Data)
    FR@10 (inter-ocular)· uses extra data· 2021-12-06
    1.76
    best: 3.12 (LUVLi)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • Facial Recognition and ModellingonWFW (Extra Data)
    NME (inter-ocular)· uses extra data· 2021-12-06
    3.96
    best: 4.57 (VGG-F)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • Facial Recognition and ModellingonAFLW-19
    NME_box (%, Full)· uses extra data· 2021-12-06
    1.334
    best: 4.04 (SAN)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • Facial Recognition and ModellingonAFLW-19
    NME_diag (%, Frontal)· uses extra data· 2021-12-06
    0.821
    best: 2.68 (CFSS)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • Facial Recognition and ModellingonAFLW-19
    NME_diag (%, Full)· uses extra data· 2021-12-06
    0.943
    best: 3.92 (CFSS)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • Facial Recognition and Modellingon300W
    NME_inter-ocular (%, Challenge)· uses extra data· 2021-12-06
    4.45
    best: 8.2 (ASMNet)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • Facial Recognition and Modellingon300W
    NME_inter-ocular (%, Common)· uses extra data· 2021-12-06
    2.56
    best: 5.09 (3DDFA)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • Facial Recognition and Modellingon300W
    NME_inter-ocular (%, Full)· uses extra data· 2021-12-06
    2.93
    best: 5.63 (3DDFA)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • Facial Recognition and Modellingon300W
    NME_inter-pupil (%, Challenge)· uses extra data· 2021-12-06
    6.42
    best: 10.59 (3DDFA)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • Facial Recognition and Modellingon300W
    NME_inter-pupil (%, Common)· uses extra data· 2021-12-06
    3.53
    best: 6.15 (3DDFA)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • Facial Recognition and Modellingon300W
    NME_inter-pupil (%, Full)· uses extra data· 2021-12-06
    4.11
    best: 7.01 (3DDFA)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109

Methodology13 results

  • 3DonAFLW-19
    AUC_box@0.07 (%, Full)· uses extra data· 2021-12-06
    81.3
    best: 81.8 (FiFA)
    SOTA
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3Don300W
    NME_inter-ocular (%, Challenge)· uses extra data· 2021-12-06
    4.45
    best: 8.2 (ASMNet)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3Don300W
    NME_inter-ocular (%, Common)· uses extra data· 2021-12-06
    2.56
    best: 5.09 (3DDFA)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3Don300W
    NME_inter-ocular (%, Full)· uses extra data· 2021-12-06
    2.93
    best: 5.63 (3DDFA)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3Don300W
    NME_inter-pupil (%, Challenge)· uses extra data· 2021-12-06
    6.42
    best: 10.59 (3DDFA)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3Don300W
    NME_inter-pupil (%, Common)· uses extra data· 2021-12-06
    3.53
    best: 6.15 (3DDFA)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3Don300W
    NME_inter-pupil (%, Full)· uses extra data· 2021-12-06
    4.11
    best: 7.01 (3DDFA)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3DonWFW (Extra Data)
    AUC@10 (inter-ocular)· uses extra data· 2021-12-06
    61.16
    best: 63.1 (SH-FAN)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3DonWFW (Extra Data)
    FR@10 (inter-ocular)· uses extra data· 2021-12-06
    1.76
    best: 3.12 (LUVLi)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3DonWFW (Extra Data)
    NME (inter-ocular)· uses extra data· 2021-12-06
    3.96
    best: 4.57 (VGG-F)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3DonAFLW-19
    NME_box (%, Full)· uses extra data· 2021-12-06
    1.334
    best: 4.04 (SAN)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3DonAFLW-19
    NME_diag (%, Frontal)· uses extra data· 2021-12-06
    0.821
    best: 2.68 (CFSS)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3DonAFLW-19
    NME_diag (%, Full)· uses extra data· 2021-12-06
    0.943
    best: 3.92 (CFSS)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109

Medical13 results

  • 3D Face ModellingonAFLW-19
    AUC_box@0.07 (%, Full)· uses extra data· 2021-12-06
    81.3
    best: 81.8 (FiFA)
    SOTA
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3D Face ModellingonWFW (Extra Data)
    AUC@10 (inter-ocular)· uses extra data· 2021-12-06
    61.16
    best: 63.1 (SH-FAN)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3D Face ModellingonWFW (Extra Data)
    FR@10 (inter-ocular)· uses extra data· 2021-12-06
    1.76
    best: 3.12 (LUVLi)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3D Face ModellingonWFW (Extra Data)
    NME (inter-ocular)· uses extra data· 2021-12-06
    3.96
    best: 4.57 (VGG-F)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3D Face ModellingonAFLW-19
    NME_box (%, Full)· uses extra data· 2021-12-06
    1.334
    best: 4.04 (SAN)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3D Face ModellingonAFLW-19
    NME_diag (%, Frontal)· uses extra data· 2021-12-06
    0.821
    best: 2.68 (CFSS)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3D Face ModellingonAFLW-19
    NME_diag (%, Full)· uses extra data· 2021-12-06
    0.943
    best: 3.92 (CFSS)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3D Face Modellingon300W
    NME_inter-ocular (%, Challenge)· uses extra data· 2021-12-06
    4.45
    best: 8.2 (ASMNet)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3D Face Modellingon300W
    NME_inter-ocular (%, Common)· uses extra data· 2021-12-06
    2.56
    best: 5.09 (3DDFA)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3D Face Modellingon300W
    NME_inter-ocular (%, Full)· uses extra data· 2021-12-06
    2.93
    best: 5.63 (3DDFA)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3D Face Modellingon300W
    NME_inter-pupil (%, Challenge)· uses extra data· 2021-12-06
    6.42
    best: 10.59 (3DDFA)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3D Face Modellingon300W
    NME_inter-pupil (%, Common)· uses extra data· 2021-12-06
    3.53
    best: 6.15 (3DDFA)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109
  • 3D Face Modellingon300W
    NME_inter-pupil (%, Full)· uses extra data· 2021-12-06
    4.11
    best: 7.01 (3DDFA)
    General Facial Representation Learning in a Visual-Linguistic MannerarXiv:2112.03109