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/TS-SAN

TS-SAN

Reported on 16 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 Vision6 results

  • VideoonNTU RGB+D
    Accuracy (CS)· 2019-12-18
    87.2
    best: 94.3 (Hulk(Finetune, ViT-L))
    Self-Attention Network for Skeleton-based Human Action RecognitionarXiv:1912.08435
  • VideoonNTU RGB+D
    Accuracy (CV)· 2019-12-18
    92.7
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Self-Attention Network for Skeleton-based Human Action RecognitionarXiv:1912.08435
  • Temporal Action LocalizationonNTU RGB+D
    Accuracy (CS)· 2019-12-18
    87.2
    best: 94.3 (Hulk(Finetune, ViT-L))
    Self-Attention Network for Skeleton-based Human Action RecognitionarXiv:1912.08435
  • Temporal Action LocalizationonNTU RGB+D
    Accuracy (CV)· 2019-12-18
    92.7
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Self-Attention Network for Skeleton-based Human Action RecognitionarXiv:1912.08435
  • Action LocalizationonNTU RGB+D
    Accuracy (CS)· 2019-12-18
    87.2
    best: 94.3 (Hulk(Finetune, ViT-L))
    Self-Attention Network for Skeleton-based Human Action RecognitionarXiv:1912.08435
  • Action LocalizationonNTU RGB+D
    Accuracy (CV)· 2019-12-18
    92.7
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Self-Attention Network for Skeleton-based Human Action RecognitionarXiv:1912.08435

Time Series4 results

  • Action DetectiononNTU RGB+D
    Accuracy (CS)· 2019-12-18
    87.2
    best: 94.3 (Hulk(Finetune, ViT-L))
    Self-Attention Network for Skeleton-based Human Action RecognitionarXiv:1912.08435
  • Action DetectiononNTU RGB+D
    Accuracy (CV)· 2019-12-18
    92.7
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Self-Attention Network for Skeleton-based Human Action RecognitionarXiv:1912.08435
  • Action RecognitiononNTU RGB+D
    Accuracy (CS)· 2019-12-18
    87.2
    best: 97.4 (DSCNet (RGB + Pose))
    Self-Attention Network for Skeleton-based Human Action RecognitionarXiv:1912.08435
  • Action RecognitiononNTU RGB+D
    Accuracy (CV)· 2019-12-18
    92.7
    best: 99.6 (PoseC3D (RGB + Pose))
    Self-Attention Network for Skeleton-based Human Action RecognitionarXiv:1912.08435

Methodology2 results

  • Zero-Shot LearningonNTU RGB+D
    Accuracy (CS)· 2019-12-18
    87.2
    best: 94.3 (Hulk(Finetune, ViT-L))
    Self-Attention Network for Skeleton-based Human Action RecognitionarXiv:1912.08435
  • Zero-Shot LearningonNTU RGB+D
    Accuracy (CV)· 2019-12-18
    92.7
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Self-Attention Network for Skeleton-based Human Action RecognitionarXiv:1912.08435

Robots2 results

  • Activity RecognitiononNTU RGB+D
    Accuracy (CS)· 2019-12-18
    87.2
    best: 97.4 (DSCNet (RGB + Pose))
    Self-Attention Network for Skeleton-based Human Action RecognitionarXiv:1912.08435
  • Activity RecognitiononNTU RGB+D
    Accuracy (CV)· 2019-12-18
    92.7
    best: 99.6 (PoseC3D (RGB + Pose))
    Self-Attention Network for Skeleton-based Human Action RecognitionarXiv:1912.08435

Natural Language Processing2 results

  • 3D Action RecognitiononNTU RGB+D
    Accuracy (CS)· 2019-12-18
    87.2
    best: 94.3 (Hulk(Finetune, ViT-L))
    Self-Attention Network for Skeleton-based Human Action RecognitionarXiv:1912.08435
  • 3D Action RecognitiononNTU RGB+D
    Accuracy (CV)· 2019-12-18
    92.7
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Self-Attention Network for Skeleton-based Human Action RecognitionarXiv:1912.08435