Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/DG-STGCN

DG-STGCN

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)· 2022-10-12
91.3
best: 92.2 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
VideoonNTU RGB+D 120
Accuracy (Cross-Subject)· 2022-10-12
89.6
best: 90.9 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
VideoonNTU RGB+D 120
Ensembled Modalities· 2022-10-12
4
best: 6 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
VideoonNTU RGB+D
Accuracy (CS)· 2022-10-12
93.2
best: 94.3 (Hulk(Finetune, ViT-L))
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
VideoonNTU RGB+D
Accuracy (CV)· 2022-10-12
97.5
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
VideoonNTU RGB+D
Ensembled Modalities· 2022-10-12
4
best: 6 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Temporal Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Setup)· 2022-10-12
91.3
best: 92.2 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Temporal Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Subject)· 2022-10-12
89.6
best: 90.9 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Temporal Action LocalizationonNTU RGB+D 120
Ensembled Modalities· 2022-10-12
4
best: 6 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Temporal Action LocalizationonNTU RGB+D
Accuracy (CS)· 2022-10-12
93.2
best: 94.3 (Hulk(Finetune, ViT-L))
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Temporal Action LocalizationonNTU RGB+D
Accuracy (CV)· 2022-10-12
97.5
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Temporal Action LocalizationonNTU RGB+D
Ensembled Modalities· 2022-10-12
4
best: 6 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Setup)· 2022-10-12
91.3
best: 92.2 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Subject)· 2022-10-12
89.6
best: 90.9 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Action LocalizationonNTU RGB+D 120
Ensembled Modalities· 2022-10-12
4
best: 6 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Action LocalizationonNTU RGB+D
Accuracy (CS)· 2022-10-12
93.2
best: 94.3 (Hulk(Finetune, ViT-L))
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Action LocalizationonNTU RGB+D
Accuracy (CV)· 2022-10-12
97.5
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Action LocalizationonNTU RGB+D
Ensembled Modalities· 2022-10-12
4
best: 6 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895

Time Series12 results

Action DetectiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2022-10-12
91.3
best: 92.2 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Action DetectiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2022-10-12
89.6
best: 90.9 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Action DetectiononNTU RGB+D 120
Ensembled Modalities· 2022-10-12
4
best: 6 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Action DetectiononNTU RGB+D
Accuracy (CS)· 2022-10-12
93.2
best: 94.3 (Hulk(Finetune, ViT-L))
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Action DetectiononNTU RGB+D
Accuracy (CV)· 2022-10-12
97.5
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Action DetectiononNTU RGB+D
Ensembled Modalities· 2022-10-12
4
best: 6 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2022-10-12
91.3
best: 96.7 (DSCNet (RGB + Pose))
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2022-10-12
89.6
best: 95.6 (DSCNet (RGB + Pose))
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Action RecognitiononNTU RGB+D 120
Ensembled Modalities· 2022-10-12
4
best: 6 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Action RecognitiononNTU RGB+D
Accuracy (CS)· 2022-10-12
93.2
best: 97.4 (DSCNet (RGB + Pose))
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Action RecognitiononNTU RGB+D
Accuracy (CV)· 2022-10-12
97.5
best: 99.6 (PoseC3D (RGB + Pose))
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Action RecognitiononNTU RGB+D
Ensembled Modalities· 2022-10-12
4
best: 6 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895

Methodology6 results

Zero-Shot LearningonNTU RGB+D 120
Accuracy (Cross-Setup)· 2022-10-12
91.3
best: 92.2 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Zero-Shot LearningonNTU RGB+D 120
Accuracy (Cross-Subject)· 2022-10-12
89.6
best: 90.9 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Zero-Shot LearningonNTU RGB+D 120
Ensembled Modalities· 2022-10-12
4
best: 6 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Zero-Shot LearningonNTU RGB+D
Accuracy (CS)· 2022-10-12
93.2
best: 94.3 (Hulk(Finetune, ViT-L))
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Zero-Shot LearningonNTU RGB+D
Accuracy (CV)· 2022-10-12
97.5
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Zero-Shot LearningonNTU RGB+D
Ensembled Modalities· 2022-10-12
4
best: 6 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895

Robots6 results

Activity RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2022-10-12
91.3
best: 96.7 (DSCNet (RGB + Pose))
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Activity RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2022-10-12
89.6
best: 95.6 (DSCNet (RGB + Pose))
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Activity RecognitiononNTU RGB+D 120
Ensembled Modalities· 2022-10-12
4
best: 6 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Activity RecognitiononNTU RGB+D
Accuracy (CS)· 2022-10-12
93.2
best: 97.4 (DSCNet (RGB + Pose))
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Activity RecognitiononNTU RGB+D
Accuracy (CV)· 2022-10-12
97.5
best: 99.6 (PoseC3D (RGB + Pose))
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
Activity RecognitiononNTU RGB+D
Ensembled Modalities· 2022-10-12
4
best: 6 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895

Natural Language Processing6 results

3D Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2022-10-12
91.3
best: 92.2 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
3D Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2022-10-12
89.6
best: 90.9 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
3D Action RecognitiononNTU RGB+D 120
Ensembled Modalities· 2022-10-12
4
best: 6 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
3D Action RecognitiononNTU RGB+D
Accuracy (CS)· 2022-10-12
93.2
best: 94.3 (Hulk(Finetune, ViT-L))
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
3D Action RecognitiononNTU RGB+D
Accuracy (CV)· 2022-10-12
97.5
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895
3D Action RecognitiononNTU RGB+D
Ensembled Modalities· 2022-10-12
4
best: 6 (ProtoGCN)
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition arXiv:2210.05895