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/CHASE(CTR-GCN)

CHASE(CTR-GCN)

Reported on 13 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 Vision7 results

  • VideoonAssembly101
    Actions Top-1· 2024-10-09
    28.03
    best: 41.06 (HandFormer-B/21)
    CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action RecognitionarXiv:2410.07153
  • Temporal Action LocalizationonAssembly101
    Actions Top-1· 2024-10-09
    28.03
    best: 41.06 (HandFormer-B/21)
    CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action RecognitionarXiv:2410.07153
  • Action LocalizationonAssembly101
    Actions Top-1· 2024-10-09
    28.03
    best: 41.06 (HandFormer-B/21)
    CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action RecognitionarXiv:2410.07153
  • Human Interaction RecognitiononNTU RGB+D
    Accuracy (Cross-Subject)· 2024-10-09
    96.5
    best: 97.1 (SkateFormer)
    CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action RecognitionarXiv:2410.07153
  • Human Interaction RecognitiononNTU RGB+D
    Accuracy (Cross-View)· 2024-10-09
    98.8
    best: 99.3 (SkateFormer)
    CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action RecognitionarXiv:2410.07153
  • Human Interaction RecognitiononNTU RGB+D 120
    Accuracy (Cross-Setup)· 2024-10-09
    92.3
    best: 93.2 (SkateFormer)
    CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action RecognitionarXiv:2410.07153
  • Human Interaction RecognitiononNTU RGB+D 120
    Accuracy (Cross-Subject)· 2024-10-09
    91.3
    best: 92.3 (SkateFormer)
    CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action RecognitionarXiv:2410.07153

Robots3 results

  • Activity RecognitiononAssembly101
    Actions Top-1· 2024-10-09
    28.03
    best: 41.06 (HandFormer-B/21)
    CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action RecognitionarXiv:2410.07153
  • Activity RecognitiononCollective Activity
    Accuracy· 2024-10-09
    89.61
    best: 96.5 (Tamura et al.)
    CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action RecognitionarXiv:2410.07153
  • Activity RecognitiononVolleyball
    Accuracy· 2024-10-09
    92.89
    best: 96 (Tamura et al.)
    CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action RecognitionarXiv:2410.07153

Methodology1 result

  • Zero-Shot LearningonAssembly101
    Actions Top-1· 2024-10-09
    28.03
    best: 41.06 (HandFormer-B/21)
    CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action RecognitionarXiv:2410.07153

Natural Language Processing1 result

  • 3D Action RecognitiononAssembly101
    Actions Top-1· 2024-10-09
    28.03
    best: 41.06 (HandFormer-B/21)
    CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action RecognitionarXiv:2410.07153

Time Series1 result

  • Action RecognitiononAssembly101
    Actions Top-1· 2024-10-09
    28.03
    best: 41.06 (HandFormer-B/21)
    CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action RecognitionarXiv:2410.07153