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/TD-GCN

TD-GCN

Reported on 68 benchmarks across 10 tasks

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

Computer Vision28 results

  • VideoonUAV-Human
    CSv1(%)
    45.43
    best: 47.96 (HDBN)
  • VideoonUAV-Human
    CSv2(%)
    72.86
    best: 75.36 (HDBN)
  • VideoonSHREC 2017 track on 3D Hand Gesture Recognition
    14 gestures accuracy
    97.02
    best: 99.85 (RE-TCN)
  • VideoonSHREC 2017 track on 3D Hand Gesture Recognition
    28 gestures accuracy
    95.36
    best: 99.95 (RE-TCN)
  • VideoonN-UCLA
    Accuracy
    97.4
    best: 99.1 (DSCNet (RGB + Pose))
  • VideoonNTU RGB+D
    Accuracy (CS)
    92.8
    best: 94.3 (Hulk(Finetune, ViT-L))
  • VideoonNTU RGB+D
    Accuracy (CV)
    96.8
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
  • VideoonNTU RGB+D
    Ensembled Modalities
    4
    best: 6 (ProtoGCN)
  • Temporal Action LocalizationonUAV-Human
    CSv1(%)
    45.43
    best: 47.96 (HDBN)
  • Temporal Action LocalizationonUAV-Human
    CSv2(%)
    72.86
    best: 75.36 (HDBN)
  • Temporal Action LocalizationonSHREC 2017 track on 3D Hand Gesture Recognition
    14 gestures accuracy
    97.02
    best: 99.85 (RE-TCN)
  • Temporal Action LocalizationonSHREC 2017 track on 3D Hand Gesture Recognition
    28 gestures accuracy
    95.36
    best: 99.95 (RE-TCN)
  • Temporal Action LocalizationonN-UCLA
    Accuracy
    97.4
    best: 99.1 (DSCNet (RGB + Pose))
  • Temporal Action LocalizationonNTU RGB+D
    Accuracy (CS)
    92.8
    best: 94.3 (Hulk(Finetune, ViT-L))
  • Temporal Action LocalizationonNTU RGB+D
    Accuracy (CV)
    96.8
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
  • Temporal Action LocalizationonNTU RGB+D
    Ensembled Modalities
    4
    best: 6 (ProtoGCN)
  • Action LocalizationonUAV-Human
    CSv1(%)
    45.43
    best: 47.96 (HDBN)
  • Action LocalizationonUAV-Human
    CSv2(%)
    72.86
    best: 75.36 (HDBN)
  • Action LocalizationonSHREC 2017 track on 3D Hand Gesture Recognition
    14 gestures accuracy
    97.02
    best: 99.85 (RE-TCN)
  • Action LocalizationonSHREC 2017 track on 3D Hand Gesture Recognition
    28 gestures accuracy
    95.36
    best: 99.95 (RE-TCN)
  • Action LocalizationonN-UCLA
    Accuracy
    97.4
    best: 99.1 (DSCNet (RGB + Pose))
  • Action LocalizationonNTU RGB+D
    Accuracy (CS)
    92.8
    best: 94.3 (Hulk(Finetune, ViT-L))
  • Action LocalizationonNTU RGB+D
    Accuracy (CV)
    96.8
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
  • Action LocalizationonNTU RGB+D
    Ensembled Modalities
    4
    best: 6 (ProtoGCN)
  • HandonDHG-28
    Accuracy
    91.4
    best: 93.57 (DSTSA-GCN)
  • HandonDHG-14
    Accuracy
    93.9
    best: 95.83 (e2eET)
  • Gesture RecognitiononDHG-28
    Accuracy
    91.4
    best: 93.57 (DSTSA-GCN)
  • Gesture RecognitiononDHG-14
    Accuracy
    93.9
    best: 95.83 (e2eET)

Time Series16 results

  • Action DetectiononUAV-Human
    CSv1(%)
    45.43
    best: 47.96 (HDBN)
  • Action DetectiononUAV-Human
    CSv2(%)
    72.86
    best: 75.36 (HDBN)
  • Action DetectiononSHREC 2017 track on 3D Hand Gesture Recognition
    14 gestures accuracy
    97.02
    best: 99.85 (RE-TCN)
  • Action DetectiononSHREC 2017 track on 3D Hand Gesture Recognition
    28 gestures accuracy
    95.36
    best: 99.95 (RE-TCN)
  • Action DetectiononN-UCLA
    Accuracy
    97.4
    best: 99.1 (DSCNet (RGB + Pose))
  • Action DetectiononNTU RGB+D
    Accuracy (CS)
    92.8
    best: 94.3 (Hulk(Finetune, ViT-L))
  • Action DetectiononNTU RGB+D
    Accuracy (CV)
    96.8
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
  • Action DetectiononNTU RGB+D
    Ensembled Modalities
    4
    best: 6 (ProtoGCN)
  • Action RecognitiononUAV-Human
    CSv1(%)
    45.43
    best: 47.96 (HDBN)
  • Action RecognitiononUAV-Human
    CSv2(%)
    72.86
    best: 75.36 (HDBN)
  • Action RecognitiononSHREC 2017 track on 3D Hand Gesture Recognition
    14 gestures accuracy
    97.02
    best: 99.85 (RE-TCN)
  • Action RecognitiononSHREC 2017 track on 3D Hand Gesture Recognition
    28 gestures accuracy
    95.36
    best: 99.95 (RE-TCN)
  • Action RecognitiononN-UCLA
    Accuracy
    97.4
    best: 99.1 (DSCNet (RGB + Pose))
  • Action RecognitiononNTU RGB+D
    Accuracy (CS)
    92.8
    best: 97.4 (DSCNet (RGB + Pose))
  • Action RecognitiononNTU RGB+D
    Accuracy (CV)
    96.8
    best: 99.6 (PoseC3D (RGB + Pose))
  • Action RecognitiononNTU RGB+D
    Ensembled Modalities
    4
    best: 6 (ProtoGCN)

Methodology8 results

  • Zero-Shot LearningonUAV-Human
    CSv1(%)
    45.43
    best: 47.96 (HDBN)
  • Zero-Shot LearningonUAV-Human
    CSv2(%)
    72.86
    best: 75.36 (HDBN)
  • Zero-Shot LearningonSHREC 2017 track on 3D Hand Gesture Recognition
    14 gestures accuracy
    97.02
    best: 99.85 (RE-TCN)
  • Zero-Shot LearningonSHREC 2017 track on 3D Hand Gesture Recognition
    28 gestures accuracy
    95.36
    best: 99.95 (RE-TCN)
  • Zero-Shot LearningonN-UCLA
    Accuracy
    97.4
    best: 99.1 (DSCNet (RGB + Pose))
  • Zero-Shot LearningonNTU RGB+D
    Accuracy (CS)
    92.8
    best: 94.3 (Hulk(Finetune, ViT-L))
  • Zero-Shot LearningonNTU RGB+D
    Accuracy (CV)
    96.8
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
  • Zero-Shot LearningonNTU RGB+D
    Ensembled Modalities
    4
    best: 6 (ProtoGCN)

Robots8 results

  • Activity RecognitiononUAV-Human
    CSv1(%)
    45.43
    best: 47.96 (HDBN)
  • Activity RecognitiononUAV-Human
    CSv2(%)
    72.86
    best: 75.36 (HDBN)
  • Activity RecognitiononSHREC 2017 track on 3D Hand Gesture Recognition
    14 gestures accuracy
    97.02
    best: 99.85 (RE-TCN)
  • Activity RecognitiononSHREC 2017 track on 3D Hand Gesture Recognition
    28 gestures accuracy
    95.36
    best: 99.95 (RE-TCN)
  • Activity RecognitiononN-UCLA
    Accuracy
    97.4
    best: 99.1 (DSCNet (RGB + Pose))
  • Activity RecognitiononNTU RGB+D
    Accuracy (CS)
    92.8
    best: 97.4 (DSCNet (RGB + Pose))
  • Activity RecognitiononNTU RGB+D
    Accuracy (CV)
    96.8
    best: 99.6 (PoseC3D (RGB + Pose))
  • Activity RecognitiononNTU RGB+D
    Ensembled Modalities
    4
    best: 6 (ProtoGCN)

Natural Language Processing8 results

  • 3D Action RecognitiononUAV-Human
    CSv1(%)
    45.43
    best: 47.96 (HDBN)
  • 3D Action RecognitiononUAV-Human
    CSv2(%)
    72.86
    best: 75.36 (HDBN)
  • 3D Action RecognitiononSHREC 2017 track on 3D Hand Gesture Recognition
    14 gestures accuracy
    97.02
    best: 99.85 (RE-TCN)
  • 3D Action RecognitiononSHREC 2017 track on 3D Hand Gesture Recognition
    28 gestures accuracy
    95.36
    best: 99.95 (RE-TCN)
  • 3D Action RecognitiononN-UCLA
    Accuracy
    97.4
    best: 99.1 (DSCNet (RGB + Pose))
  • 3D Action RecognitiononNTU RGB+D
    Accuracy (CS)
    92.8
    best: 94.3 (Hulk(Finetune, ViT-L))
  • 3D Action RecognitiononNTU RGB+D
    Accuracy (CV)
    96.8
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
  • 3D Action RecognitiononNTU RGB+D
    Ensembled Modalities
    4
    best: 6 (ProtoGCN)