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/MSSTNet

MSSTNet

Reported on 56 benchmarks across 8 tasks

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

Computer Vision21 results

  • VideoonNTU RGB+D 120
    Accuracy (Cross-Setup)
    88.3
    best: 92.2 (ProtoGCN)
  • VideoonNTU RGB+D 120
    Accuracy (Cross-Subject)
    87.4
    best: 90.9 (ProtoGCN)
  • VideoonUAV-Human
    CSv1(%)
    43
    best: 47.96 (HDBN)
  • VideoonUAV-Human
    CSv2(%)
    70.1
    best: 75.36 (HDBN)
  • VideoonN-UCLA
    Accuracy
    95.3
    best: 99.1 (DSCNet (RGB + Pose))
  • VideoonNTU RGB+D
    Accuracy (CS)
    92.6
    best: 94.3 (Hulk(Finetune, ViT-L))
  • VideoonNTU RGB+D
    Accuracy (CV)
    97.8
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
  • Temporal Action LocalizationonNTU RGB+D 120
    Accuracy (Cross-Setup)
    88.3
    best: 92.2 (ProtoGCN)
  • Temporal Action LocalizationonNTU RGB+D 120
    Accuracy (Cross-Subject)
    87.4
    best: 90.9 (ProtoGCN)
  • Temporal Action LocalizationonUAV-Human
    CSv1(%)
    43
    best: 47.96 (HDBN)
  • Temporal Action LocalizationonUAV-Human
    CSv2(%)
    70.1
    best: 75.36 (HDBN)
  • Temporal Action LocalizationonN-UCLA
    Accuracy
    95.3
    best: 99.1 (DSCNet (RGB + Pose))
  • Temporal Action LocalizationonNTU RGB+D
    Accuracy (CS)
    92.6
    best: 94.3 (Hulk(Finetune, ViT-L))
  • Temporal Action LocalizationonNTU RGB+D
    Accuracy (CV)
    97.8
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
  • Action LocalizationonNTU RGB+D 120
    Accuracy (Cross-Setup)
    88.3
    best: 92.2 (ProtoGCN)
  • Action LocalizationonNTU RGB+D 120
    Accuracy (Cross-Subject)
    87.4
    best: 90.9 (ProtoGCN)
  • Action LocalizationonUAV-Human
    CSv1(%)
    43
    best: 47.96 (HDBN)
  • Action LocalizationonUAV-Human
    CSv2(%)
    70.1
    best: 75.36 (HDBN)
  • Action LocalizationonN-UCLA
    Accuracy
    95.3
    best: 99.1 (DSCNet (RGB + Pose))
  • Action LocalizationonNTU RGB+D
    Accuracy (CS)
    92.6
    best: 94.3 (Hulk(Finetune, ViT-L))
  • Action LocalizationonNTU RGB+D
    Accuracy (CV)
    97.8
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])

Time Series14 results

  • Action DetectiononNTU RGB+D 120
    Accuracy (Cross-Setup)
    88.3
    best: 92.2 (ProtoGCN)
  • Action DetectiononNTU RGB+D 120
    Accuracy (Cross-Subject)
    87.4
    best: 90.9 (ProtoGCN)
  • Action DetectiononUAV-Human
    CSv1(%)
    43
    best: 47.96 (HDBN)
  • Action DetectiononUAV-Human
    CSv2(%)
    70.1
    best: 75.36 (HDBN)
  • Action DetectiononN-UCLA
    Accuracy
    95.3
    best: 99.1 (DSCNet (RGB + Pose))
  • Action DetectiononNTU RGB+D
    Accuracy (CS)
    92.6
    best: 94.3 (Hulk(Finetune, ViT-L))
  • Action DetectiononNTU RGB+D
    Accuracy (CV)
    97.8
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
  • Action RecognitiononNTU RGB+D 120
    Accuracy (Cross-Setup)
    88.3
    best: 96.7 (DSCNet (RGB + Pose))
  • Action RecognitiononNTU RGB+D 120
    Accuracy (Cross-Subject)
    87.4
    best: 95.6 (DSCNet (RGB + Pose))
  • Action RecognitiononUAV-Human
    CSv1(%)
    43
    best: 47.96 (HDBN)
  • Action RecognitiononUAV-Human
    CSv2(%)
    70.1
    best: 75.36 (HDBN)
  • Action RecognitiononN-UCLA
    Accuracy
    95.3
    best: 99.1 (DSCNet (RGB + Pose))
  • Action RecognitiononNTU RGB+D
    Accuracy (CS)
    92.6
    best: 97.4 (DSCNet (RGB + Pose))
  • Action RecognitiononNTU RGB+D
    Accuracy (CV)
    97.8
    best: 99.6 (PoseC3D (RGB + Pose))

Methodology7 results

  • Zero-Shot LearningonNTU RGB+D 120
    Accuracy (Cross-Setup)
    88.3
    best: 92.2 (ProtoGCN)
  • Zero-Shot LearningonNTU RGB+D 120
    Accuracy (Cross-Subject)
    87.4
    best: 90.9 (ProtoGCN)
  • Zero-Shot LearningonUAV-Human
    CSv1(%)
    43
    best: 47.96 (HDBN)
  • Zero-Shot LearningonUAV-Human
    CSv2(%)
    70.1
    best: 75.36 (HDBN)
  • Zero-Shot LearningonN-UCLA
    Accuracy
    95.3
    best: 99.1 (DSCNet (RGB + Pose))
  • Zero-Shot LearningonNTU RGB+D
    Accuracy (CS)
    92.6
    best: 94.3 (Hulk(Finetune, ViT-L))
  • Zero-Shot LearningonNTU RGB+D
    Accuracy (CV)
    97.8
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])

Robots7 results

  • Activity RecognitiononNTU RGB+D 120
    Accuracy (Cross-Setup)
    88.3
    best: 96.7 (DSCNet (RGB + Pose))
  • Activity RecognitiononNTU RGB+D 120
    Accuracy (Cross-Subject)
    87.4
    best: 95.6 (DSCNet (RGB + Pose))
  • Activity RecognitiononUAV-Human
    CSv1(%)
    43
    best: 47.96 (HDBN)
  • Activity RecognitiononUAV-Human
    CSv2(%)
    70.1
    best: 75.36 (HDBN)
  • Activity RecognitiononN-UCLA
    Accuracy
    95.3
    best: 99.1 (DSCNet (RGB + Pose))
  • Activity RecognitiononNTU RGB+D
    Accuracy (CS)
    92.6
    best: 97.4 (DSCNet (RGB + Pose))
  • Activity RecognitiononNTU RGB+D
    Accuracy (CV)
    97.8
    best: 99.6 (PoseC3D (RGB + Pose))

Natural Language Processing7 results

  • 3D Action RecognitiononNTU RGB+D 120
    Accuracy (Cross-Setup)
    88.3
    best: 92.2 (ProtoGCN)
  • 3D Action RecognitiononNTU RGB+D 120
    Accuracy (Cross-Subject)
    87.4
    best: 90.9 (ProtoGCN)
  • 3D Action RecognitiononUAV-Human
    CSv1(%)
    43
    best: 47.96 (HDBN)
  • 3D Action RecognitiononUAV-Human
    CSv2(%)
    70.1
    best: 75.36 (HDBN)
  • 3D Action RecognitiononN-UCLA
    Accuracy
    95.3
    best: 99.1 (DSCNet (RGB + Pose))
  • 3D Action RecognitiononNTU RGB+D
    Accuracy (CS)
    92.6
    best: 94.3 (Hulk(Finetune, ViT-L))
  • 3D Action RecognitiononNTU RGB+D
    Accuracy (CV)
    97.8
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])