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/Dynamic GCN

Dynamic GCN

Reported on 24 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 Vision9 results

  • VideoonKinetics-Skeleton dataset
    Accuracy· 2020-07-29
    37.9
    best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
    Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action RecognitionarXiv:2007.14690
  • VideoonNTU RGB+D
    Accuracy (CS)· 2020-07-29
    91.5
    best: 94.3 (Hulk(Finetune, ViT-L))
    Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action RecognitionarXiv:2007.14690
  • VideoonNTU RGB+D
    Accuracy (CV)· 2020-07-29
    96
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action RecognitionarXiv:2007.14690
  • Temporal Action LocalizationonKinetics-Skeleton dataset
    Accuracy· 2020-07-29
    37.9
    best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
    Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action RecognitionarXiv:2007.14690
  • Temporal Action LocalizationonNTU RGB+D
    Accuracy (CS)· 2020-07-29
    91.5
    best: 94.3 (Hulk(Finetune, ViT-L))
    Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action RecognitionarXiv:2007.14690
  • Temporal Action LocalizationonNTU RGB+D
    Accuracy (CV)· 2020-07-29
    96
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action RecognitionarXiv:2007.14690
  • Action LocalizationonKinetics-Skeleton dataset
    Accuracy· 2020-07-29
    37.9
    best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
    Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action RecognitionarXiv:2007.14690
  • Action LocalizationonNTU RGB+D
    Accuracy (CS)· 2020-07-29
    91.5
    best: 94.3 (Hulk(Finetune, ViT-L))
    Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action RecognitionarXiv:2007.14690
  • Action LocalizationonNTU RGB+D
    Accuracy (CV)· 2020-07-29
    96
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action RecognitionarXiv:2007.14690

Time Series6 results

  • Action DetectiononKinetics-Skeleton dataset
    Accuracy· 2020-07-29
    37.9
    best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
    Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action RecognitionarXiv:2007.14690
  • Action DetectiononNTU RGB+D
    Accuracy (CS)· 2020-07-29
    91.5
    best: 94.3 (Hulk(Finetune, ViT-L))
    Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action RecognitionarXiv:2007.14690
  • Action DetectiononNTU RGB+D
    Accuracy (CV)· 2020-07-29
    96
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action RecognitionarXiv:2007.14690
  • Action RecognitiononKinetics-Skeleton dataset
    Accuracy· 2020-07-29
    37.9
    best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
    Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action RecognitionarXiv:2007.14690
  • Action RecognitiononNTU RGB+D
    Accuracy (CS)· 2020-07-29
    91.5
    best: 97.4 (DSCNet (RGB + Pose))
    Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action RecognitionarXiv:2007.14690
  • Action RecognitiononNTU RGB+D
    Accuracy (CV)· 2020-07-29
    96
    best: 99.6 (PoseC3D (RGB + Pose))
    Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action RecognitionarXiv:2007.14690

Methodology3 results

  • Zero-Shot LearningonKinetics-Skeleton dataset
    Accuracy· 2020-07-29
    37.9
    best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
    Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action RecognitionarXiv:2007.14690
  • Zero-Shot LearningonNTU RGB+D
    Accuracy (CS)· 2020-07-29
    91.5
    best: 94.3 (Hulk(Finetune, ViT-L))
    Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action RecognitionarXiv:2007.14690
  • Zero-Shot LearningonNTU RGB+D
    Accuracy (CV)· 2020-07-29
    96
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action RecognitionarXiv:2007.14690

Robots3 results

  • Activity RecognitiononKinetics-Skeleton dataset
    Accuracy· 2020-07-29
    37.9
    best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
    Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action RecognitionarXiv:2007.14690
  • Activity RecognitiononNTU RGB+D
    Accuracy (CS)· 2020-07-29
    91.5
    best: 97.4 (DSCNet (RGB + Pose))
    Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action RecognitionarXiv:2007.14690
  • Activity RecognitiononNTU RGB+D
    Accuracy (CV)· 2020-07-29
    96
    best: 99.6 (PoseC3D (RGB + Pose))
    Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action RecognitionarXiv:2007.14690

Natural Language Processing3 results

  • 3D Action RecognitiononKinetics-Skeleton dataset
    Accuracy· 2020-07-29
    37.9
    best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
    Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action RecognitionarXiv:2007.14690
  • 3D Action RecognitiononNTU RGB+D
    Accuracy (CS)· 2020-07-29
    91.5
    best: 94.3 (Hulk(Finetune, ViT-L))
    Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action RecognitionarXiv:2007.14690
  • 3D Action RecognitiononNTU RGB+D
    Accuracy (CV)· 2020-07-29
    96
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action RecognitionarXiv:2007.14690