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/Zhang et al.

Zhang et al.

Reported on 16 benchmarks across 13 tasks · 4 papers · 7 SOTA

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

Computer Vision10 results

  • 3D Human Pose EstimationonShelf
    PCP3D· 2021-08-23
    98.1
    best: 100 (RapidPoseTriangulation (with corrected labels))
    SOTA
    Lightweight Multi-person Total Motion Capture Using Sparse Multi-view CamerasarXiv:2108.10378
  • Pose EstimationonShelf
    PCP3D· 2021-08-23
    98.1
    best: 100 (RapidPoseTriangulation (with corrected labels))
    SOTA
    Lightweight Multi-person Total Motion Capture Using Sparse Multi-view CamerasarXiv:2108.10378
  • 3D Multi-Person Pose EstimationonShelf
    PCP3D· 2021-08-23
    98.1
    best: 100 (RapidPoseTriangulation (with corrected labels))
    SOTA
    Lightweight Multi-person Total Motion Capture Using Sparse Multi-view CamerasarXiv:2108.10378
  • Image EditingonISTD
    MAE· 2022-06-22
    6.62
    best: 4.79 (ShadowFormer)
    SpA-Former: Transformer image shadow detection and removal via spatial attentionarXiv:2206.10910
  • Shadow RemovalonISTD
    MAE· 2022-06-22
    6.62
    best: 4.79 (ShadowFormer)
    SpA-Former: Transformer image shadow detection and removal via spatial attentionarXiv:2206.10910
  • Pedestrian DetectiononCaltech
    Reasonable Miss Rate· 2017-02-19
    5.8
    best: 24.8 (LDCF)
    CityPersons: A Diverse Dataset for Pedestrian DetectionarXiv:1702.05693
  • CrowdsonShanghaiTech B
    MAE
    32
    best: 5.51 (EBC-ZIP-B)
  • CrowdsonShanghaiTech A
    MAE
    181.8
    best: 47.81 (EBC-ZIP-B)
  • CrowdsonUCF CC 50
    MAE
    467
    best: 154.8 (APGCC)
  • CrowdsonWorldExpo’10
    Average MAE
    12.9
    best: 7.2 (ECAN)

Methodology2 results

  • 3DonShelf
    PCP3D· 2021-08-23
    98.1
    best: 100 (RapidPoseTriangulation (with corrected labels))
    SOTA
    Lightweight Multi-person Total Motion Capture Using Sparse Multi-view CamerasarXiv:2108.10378
  • 16konISTD
    MAE· 2022-06-22
    6.62
    best: 4.79 (ShadowFormer)
    SpA-Former: Transformer image shadow detection and removal via spatial attentionarXiv:2206.10910

Natural Language Processing2 results

  • Semantic ParsingonLDC2017T10
    Smatch· 2019-09-05
    77
    best: 86.7 (StructBART + MBSE (IBM))
    SOTA
    Broad-Coverage Semantic Parsing as TransductionarXiv:1909.02607
  • AMR ParsingonLDC2017T10
    Smatch· 2019-09-05
    77
    best: 86.7 (StructBART + MBSE (IBM))
    SOTA
    Broad-Coverage Semantic Parsing as TransductionarXiv:1909.02607

Audio1 result

  • 1 Image, 2*2 StitchionShelf
    PCP3D· 2021-08-23
    98.1
    best: 100 (RapidPoseTriangulation (with corrected labels))
    SOTA
    Lightweight Multi-person Total Motion Capture Using Sparse Multi-view CamerasarXiv:2108.10378

Robots1 result

  • Autonomous VehiclesonCaltech
    Reasonable Miss Rate· 2017-02-19
    5.8
    best: 24.8 (LDCF)
    CityPersons: A Diverse Dataset for Pedestrian DetectionarXiv:1702.05693