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/AngNet-JA + BA + JBA + VJBA

AngNet-JA + BA + JBA + VJBA

Reported on 24 benchmarks across 8 tasks · 1 paper · 8 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
Ensembled Modalities· 2021-05-04
4
best: 6 (ProtoGCN)
SOTA
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition arXiv:2105.01563
Temporal Action LocalizationonNTU RGB+D 120
Ensembled Modalities· 2021-05-04
4
best: 6 (ProtoGCN)
SOTA
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition arXiv:2105.01563
Action LocalizationonNTU RGB+D 120
Ensembled Modalities· 2021-05-04
4
best: 6 (ProtoGCN)
SOTA
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition arXiv:2105.01563
VideoonNTU RGB+D
Accuracy (CS)· uses extra data· 2021-05-04
91.7
best: 94.3 (Hulk(Finetune, ViT-L))
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition arXiv:2105.01563
VideoonNTU RGB+D
Accuracy (CV)· uses extra data· 2021-05-04
96.4
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition arXiv:2105.01563
Temporal Action LocalizationonNTU RGB+D
Accuracy (CS)· uses extra data· 2021-05-04
91.7
best: 94.3 (Hulk(Finetune, ViT-L))
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition arXiv:2105.01563
Temporal Action LocalizationonNTU RGB+D
Accuracy (CV)· uses extra data· 2021-05-04
96.4
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition arXiv:2105.01563
Action LocalizationonNTU RGB+D
Accuracy (CS)· uses extra data· 2021-05-04
91.7
best: 94.3 (Hulk(Finetune, ViT-L))
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition arXiv:2105.01563
Action LocalizationonNTU RGB+D
Accuracy (CV)· uses extra data· 2021-05-04
96.4
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition arXiv:2105.01563

Time Series6 results

Action DetectiononNTU RGB+D 120
Ensembled Modalities· 2021-05-04
4
best: 6 (ProtoGCN)
SOTA
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition arXiv:2105.01563
Action RecognitiononNTU RGB+D 120
Ensembled Modalities· 2021-05-04
4
best: 6 (ProtoGCN)
SOTA
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition arXiv:2105.01563
Action DetectiononNTU RGB+D
Accuracy (CS)· uses extra data· 2021-05-04
91.7
best: 94.3 (Hulk(Finetune, ViT-L))
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition arXiv:2105.01563
Action DetectiononNTU RGB+D
Accuracy (CV)· uses extra data· 2021-05-04
96.4
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition arXiv:2105.01563
Action RecognitiononNTU RGB+D
Accuracy (CS)· uses extra data· 2021-05-04
91.7
best: 97.4 (DSCNet (RGB + Pose))
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition arXiv:2105.01563
Action RecognitiononNTU RGB+D
Accuracy (CV)· uses extra data· 2021-05-04
96.4
best: 99.6 (PoseC3D (RGB + Pose))
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition arXiv:2105.01563

Methodology3 results

Zero-Shot LearningonNTU RGB+D 120
Ensembled Modalities· 2021-05-04
4
best: 6 (ProtoGCN)
SOTA
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition arXiv:2105.01563
Zero-Shot LearningonNTU RGB+D
Accuracy (CS)· uses extra data· 2021-05-04
91.7
best: 94.3 (Hulk(Finetune, ViT-L))
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition arXiv:2105.01563
Zero-Shot LearningonNTU RGB+D
Accuracy (CV)· uses extra data· 2021-05-04
96.4
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition arXiv:2105.01563

Robots3 results

Activity RecognitiononNTU RGB+D 120
Ensembled Modalities· 2021-05-04
4
best: 6 (ProtoGCN)
SOTA
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition arXiv:2105.01563
Activity RecognitiononNTU RGB+D
Accuracy (CS)· uses extra data· 2021-05-04
91.7
best: 97.4 (DSCNet (RGB + Pose))
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition arXiv:2105.01563
Activity RecognitiononNTU RGB+D
Accuracy (CV)· uses extra data· 2021-05-04
96.4
best: 99.6 (PoseC3D (RGB + Pose))
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition arXiv:2105.01563

Natural Language Processing3 results

3D Action RecognitiononNTU RGB+D 120
Ensembled Modalities· 2021-05-04
4
best: 6 (ProtoGCN)
SOTA
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition arXiv:2105.01563
3D Action RecognitiononNTU RGB+D
Accuracy (CS)· uses extra data· 2021-05-04
91.7
best: 94.3 (Hulk(Finetune, ViT-L))
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition arXiv:2105.01563
3D Action RecognitiononNTU RGB+D
Accuracy (CV)· uses extra data· 2021-05-04
96.4
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition arXiv:2105.01563