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/Five Spatial Skeleton Features

Five Spatial Skeleton Features

Reported on 8 benchmarks across 8 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

  • VideoonNTU RGB+D
    Accuracy (CV)· 2017-05-02
    82.31
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Investigation of Different Skeleton Features for CNN-based 3D Action RecognitionarXiv:1705.00835
  • Temporal Action LocalizationonNTU RGB+D
    Accuracy (CV)· 2017-05-02
    82.31
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Investigation of Different Skeleton Features for CNN-based 3D Action RecognitionarXiv:1705.00835
  • Action LocalizationonNTU RGB+D
    Accuracy (CV)· 2017-05-02
    82.31
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Investigation of Different Skeleton Features for CNN-based 3D Action RecognitionarXiv:1705.00835

Time Series2 results

  • Action DetectiononNTU RGB+D
    Accuracy (CV)· 2017-05-02
    82.31
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Investigation of Different Skeleton Features for CNN-based 3D Action RecognitionarXiv:1705.00835
  • Action RecognitiononNTU RGB+D
    Accuracy (CV)· 2017-05-02
    82.31
    best: 99.6 (PoseC3D (RGB + Pose))
    Investigation of Different Skeleton Features for CNN-based 3D Action RecognitionarXiv:1705.00835

Methodology1 result

  • Zero-Shot LearningonNTU RGB+D
    Accuracy (CV)· 2017-05-02
    82.31
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Investigation of Different Skeleton Features for CNN-based 3D Action RecognitionarXiv:1705.00835

Robots1 result

  • Activity RecognitiononNTU RGB+D
    Accuracy (CV)· 2017-05-02
    82.31
    best: 99.6 (PoseC3D (RGB + Pose))
    Investigation of Different Skeleton Features for CNN-based 3D Action RecognitionarXiv:1705.00835

Natural Language Processing1 result

  • 3D Action RecognitiononNTU RGB+D
    Accuracy (CV)· 2017-05-02
    82.31
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Investigation of Different Skeleton Features for CNN-based 3D Action RecognitionarXiv:1705.00835