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/DualHead-Net

DualHead-Net

Reported on 48 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 Vision18 results

  • VideoonNTU RGB+D 120
    Accuracy (Cross-Setup)· 2021-08-10
    89.3
    best: 92.2 (ProtoGCN)
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • VideoonNTU RGB+D 120
    Accuracy (Cross-Subject)· 2021-08-10
    88.2
    best: 90.9 (ProtoGCN)
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • VideoonNTU RGB+D 120
    Ensembled Modalities· 2021-08-10
    4
    best: 6 (ProtoGCN)
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • VideoonKinetics-Skeleton dataset
    Accuracy· 2021-08-10
    38.4
    best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • VideoonNTU RGB+D
    Accuracy (CS)· 2021-08-10
    92
    best: 94.3 (Hulk(Finetune, ViT-L))
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • VideoonNTU RGB+D
    Accuracy (CV)· 2021-08-10
    96.6
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Temporal Action LocalizationonNTU RGB+D 120
    Accuracy (Cross-Setup)· 2021-08-10
    89.3
    best: 92.2 (ProtoGCN)
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Temporal Action LocalizationonNTU RGB+D 120
    Accuracy (Cross-Subject)· 2021-08-10
    88.2
    best: 90.9 (ProtoGCN)
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Temporal Action LocalizationonNTU RGB+D 120
    Ensembled Modalities· 2021-08-10
    4
    best: 6 (ProtoGCN)
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Temporal Action LocalizationonKinetics-Skeleton dataset
    Accuracy· 2021-08-10
    38.4
    best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Temporal Action LocalizationonNTU RGB+D
    Accuracy (CS)· 2021-08-10
    92
    best: 94.3 (Hulk(Finetune, ViT-L))
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Temporal Action LocalizationonNTU RGB+D
    Accuracy (CV)· 2021-08-10
    96.6
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Action LocalizationonNTU RGB+D 120
    Accuracy (Cross-Setup)· 2021-08-10
    89.3
    best: 92.2 (ProtoGCN)
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Action LocalizationonNTU RGB+D 120
    Accuracy (Cross-Subject)· 2021-08-10
    88.2
    best: 90.9 (ProtoGCN)
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Action LocalizationonNTU RGB+D 120
    Ensembled Modalities· 2021-08-10
    4
    best: 6 (ProtoGCN)
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Action LocalizationonKinetics-Skeleton dataset
    Accuracy· 2021-08-10
    38.4
    best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Action LocalizationonNTU RGB+D
    Accuracy (CS)· 2021-08-10
    92
    best: 94.3 (Hulk(Finetune, ViT-L))
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Action LocalizationonNTU RGB+D
    Accuracy (CV)· 2021-08-10
    96.6
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536

Time Series12 results

  • Action DetectiononNTU RGB+D 120
    Accuracy (Cross-Setup)· 2021-08-10
    89.3
    best: 92.2 (ProtoGCN)
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Action DetectiononNTU RGB+D 120
    Accuracy (Cross-Subject)· 2021-08-10
    88.2
    best: 90.9 (ProtoGCN)
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Action DetectiononNTU RGB+D 120
    Ensembled Modalities· 2021-08-10
    4
    best: 6 (ProtoGCN)
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Action DetectiononKinetics-Skeleton dataset
    Accuracy· 2021-08-10
    38.4
    best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Action DetectiononNTU RGB+D
    Accuracy (CS)· 2021-08-10
    92
    best: 94.3 (Hulk(Finetune, ViT-L))
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Action DetectiononNTU RGB+D
    Accuracy (CV)· 2021-08-10
    96.6
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Action RecognitiononNTU RGB+D 120
    Accuracy (Cross-Setup)· 2021-08-10
    89.3
    best: 96.7 (DSCNet (RGB + Pose))
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Action RecognitiononNTU RGB+D 120
    Accuracy (Cross-Subject)· 2021-08-10
    88.2
    best: 95.6 (DSCNet (RGB + Pose))
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Action RecognitiononNTU RGB+D 120
    Ensembled Modalities· 2021-08-10
    4
    best: 6 (ProtoGCN)
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Action RecognitiononKinetics-Skeleton dataset
    Accuracy· 2021-08-10
    38.4
    best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Action RecognitiononNTU RGB+D
    Accuracy (CS)· 2021-08-10
    92
    best: 97.4 (DSCNet (RGB + Pose))
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Action RecognitiononNTU RGB+D
    Accuracy (CV)· 2021-08-10
    96.6
    best: 99.6 (PoseC3D (RGB + Pose))
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536

Methodology6 results

  • Zero-Shot LearningonNTU RGB+D 120
    Accuracy (Cross-Setup)· 2021-08-10
    89.3
    best: 92.2 (ProtoGCN)
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Zero-Shot LearningonNTU RGB+D 120
    Accuracy (Cross-Subject)· 2021-08-10
    88.2
    best: 90.9 (ProtoGCN)
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Zero-Shot LearningonNTU RGB+D 120
    Ensembled Modalities· 2021-08-10
    4
    best: 6 (ProtoGCN)
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Zero-Shot LearningonKinetics-Skeleton dataset
    Accuracy· 2021-08-10
    38.4
    best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Zero-Shot LearningonNTU RGB+D
    Accuracy (CS)· 2021-08-10
    92
    best: 94.3 (Hulk(Finetune, ViT-L))
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Zero-Shot LearningonNTU RGB+D
    Accuracy (CV)· 2021-08-10
    96.6
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536

Robots6 results

  • Activity RecognitiononNTU RGB+D 120
    Accuracy (Cross-Setup)· 2021-08-10
    89.3
    best: 96.7 (DSCNet (RGB + Pose))
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Activity RecognitiononNTU RGB+D 120
    Accuracy (Cross-Subject)· 2021-08-10
    88.2
    best: 95.6 (DSCNet (RGB + Pose))
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Activity RecognitiononNTU RGB+D 120
    Ensembled Modalities· 2021-08-10
    4
    best: 6 (ProtoGCN)
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Activity RecognitiononKinetics-Skeleton dataset
    Accuracy· 2021-08-10
    38.4
    best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Activity RecognitiononNTU RGB+D
    Accuracy (CS)· 2021-08-10
    92
    best: 97.4 (DSCNet (RGB + Pose))
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • Activity RecognitiononNTU RGB+D
    Accuracy (CV)· 2021-08-10
    96.6
    best: 99.6 (PoseC3D (RGB + Pose))
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536

Natural Language Processing6 results

  • 3D Action RecognitiononNTU RGB+D 120
    Accuracy (Cross-Setup)· 2021-08-10
    89.3
    best: 92.2 (ProtoGCN)
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • 3D Action RecognitiononNTU RGB+D 120
    Accuracy (Cross-Subject)· 2021-08-10
    88.2
    best: 90.9 (ProtoGCN)
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • 3D Action RecognitiononNTU RGB+D 120
    Ensembled Modalities· 2021-08-10
    4
    best: 6 (ProtoGCN)
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • 3D Action RecognitiononKinetics-Skeleton dataset
    Accuracy· 2021-08-10
    38.4
    best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • 3D Action RecognitiononNTU RGB+D
    Accuracy (CS)· 2021-08-10
    92
    best: 94.3 (Hulk(Finetune, ViT-L))
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536
  • 3D Action RecognitiononNTU RGB+D
    Accuracy (CV)· 2021-08-10
    96.6
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionarXiv:2108.04536