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/TSGCNeXt

TSGCNeXt

Reported on 24 benchmarks across 8 tasks · 1 paper · 12 SOTA

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

Computer Vision9 results

VideoonNTU RGB+D 120
Accuracy (Cross-Setup)· 2023-04-23
91.7
best: 92.2 (ProtoGCN)
SOTA
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential arXiv:2304.11631
VideoonNTU RGB+D 120
Accuracy (Cross-Subject)· 2023-04-23
90.2
best: 90.9 (ProtoGCN)
SOTA
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential arXiv:2304.11631
Temporal Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Setup)· 2023-04-23
91.7
best: 92.2 (ProtoGCN)
SOTA
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential arXiv:2304.11631
Temporal Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Subject)· 2023-04-23
90.2
best: 90.9 (ProtoGCN)
SOTA
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential arXiv:2304.11631
Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Setup)· 2023-04-23
91.7
best: 92.2 (ProtoGCN)
SOTA
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential arXiv:2304.11631
Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Subject)· 2023-04-23
90.2
best: 90.9 (ProtoGCN)
SOTA
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential arXiv:2304.11631
VideoonNTU RGB+D 120
Ensembled Modalities· 2023-04-23
4
best: 6 (ProtoGCN)
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential arXiv:2304.11631
Temporal Action LocalizationonNTU RGB+D 120
Ensembled Modalities· 2023-04-23
4
best: 6 (ProtoGCN)
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential arXiv:2304.11631
Action LocalizationonNTU RGB+D 120
Ensembled Modalities· 2023-04-23
4
best: 6 (ProtoGCN)
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential arXiv:2304.11631

Time Series6 results

Action DetectiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2023-04-23
91.7
best: 92.2 (ProtoGCN)
SOTA
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential arXiv:2304.11631
Action DetectiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2023-04-23
90.2
best: 90.9 (ProtoGCN)
SOTA
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential arXiv:2304.11631
Action DetectiononNTU RGB+D 120
Ensembled Modalities· 2023-04-23
4
best: 6 (ProtoGCN)
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential arXiv:2304.11631
Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2023-04-23
91.7
best: 96.7 (DSCNet (RGB + Pose))
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential arXiv:2304.11631
Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2023-04-23
90.2
best: 95.6 (DSCNet (RGB + Pose))
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential arXiv:2304.11631
Action RecognitiononNTU RGB+D 120
Ensembled Modalities· 2023-04-23
4
best: 6 (ProtoGCN)
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential arXiv:2304.11631

Methodology3 results

Zero-Shot LearningonNTU RGB+D 120
Accuracy (Cross-Setup)· 2023-04-23
91.7
best: 92.2 (ProtoGCN)
SOTA
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential arXiv:2304.11631
Zero-Shot LearningonNTU RGB+D 120
Accuracy (Cross-Subject)· 2023-04-23
90.2
best: 90.9 (ProtoGCN)
SOTA
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential arXiv:2304.11631
Zero-Shot LearningonNTU RGB+D 120
Ensembled Modalities· 2023-04-23
4
best: 6 (ProtoGCN)
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential arXiv:2304.11631

Natural Language Processing3 results

3D Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2023-04-23
91.7
best: 92.2 (ProtoGCN)
SOTA
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential arXiv:2304.11631
3D Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2023-04-23
90.2
best: 90.9 (ProtoGCN)
SOTA
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential arXiv:2304.11631
3D Action RecognitiononNTU RGB+D 120
Ensembled Modalities· 2023-04-23
4
best: 6 (ProtoGCN)
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential arXiv:2304.11631

Robots3 results

Activity RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2023-04-23
91.7
best: 96.7 (DSCNet (RGB + Pose))
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential arXiv:2304.11631
Activity RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2023-04-23
90.2
best: 95.6 (DSCNet (RGB + Pose))
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential arXiv:2304.11631
Activity RecognitiononNTU RGB+D 120
Ensembled Modalities· 2023-04-23
4
best: 6 (ProtoGCN)
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential arXiv:2304.11631