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/CoAGCN* (2-stream)

CoAGCN* (2-stream)

Reported on 64 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 Vision24 results

VideoonNTU RGB+D 120
Accuracy (Cross-Setup)· 2022-03-21
82
best: 92.2 (ProtoGCN)
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
VideoonNTU RGB+D 120
Accuracy (Cross-Subject)· 2022-03-21
80.4
best: 90.9 (ProtoGCN)
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
VideoonNTU RGB+D 120
GFLOPS per prediction· 2022-03-21
0.44
best: 37.38 (AGCN (2-stream))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
VideoonKinetics-Skeleton dataset
Accuracy· 2022-03-21
27.5
best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
VideoonKinetics-Skeleton dataset
GFLOPS per prediction· 2022-03-21
0.25
best: 26.91 (AGCN (2-stream))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
VideoonNTU RGB+D
Accuracy (CS)· 2022-03-21
86
best: 94.3 (Hulk(Finetune, ViT-L))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
VideoonNTU RGB+D
Accuracy (CV)· 2022-03-21
93.1
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
VideoonNTU RGB+D
GFLOPs per pred· 2022-03-21
0.44
best: 16.73 (ST-GCN)
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Temporal Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Setup)· 2022-03-21
82
best: 92.2 (ProtoGCN)
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Temporal Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Subject)· 2022-03-21
80.4
best: 90.9 (ProtoGCN)
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Temporal Action LocalizationonNTU RGB+D 120
GFLOPS per prediction· 2022-03-21
0.44
best: 37.38 (AGCN (2-stream))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Temporal Action LocalizationonKinetics-Skeleton dataset
Accuracy· 2022-03-21
27.5
best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Temporal Action LocalizationonKinetics-Skeleton dataset
GFLOPS per prediction· 2022-03-21
0.25
best: 26.91 (AGCN (2-stream))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Temporal Action LocalizationonNTU RGB+D
Accuracy (CS)· 2022-03-21
86
best: 94.3 (Hulk(Finetune, ViT-L))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Temporal Action LocalizationonNTU RGB+D
Accuracy (CV)· 2022-03-21
93.1
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Temporal Action LocalizationonNTU RGB+D
GFLOPs per pred· 2022-03-21
0.44
best: 16.73 (ST-GCN)
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Setup)· 2022-03-21
82
best: 92.2 (ProtoGCN)
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Subject)· 2022-03-21
80.4
best: 90.9 (ProtoGCN)
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Action LocalizationonNTU RGB+D 120
GFLOPS per prediction· 2022-03-21
0.44
best: 37.38 (AGCN (2-stream))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Action LocalizationonKinetics-Skeleton dataset
Accuracy· 2022-03-21
27.5
best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Action LocalizationonKinetics-Skeleton dataset
GFLOPS per prediction· 2022-03-21
0.25
best: 26.91 (AGCN (2-stream))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Action LocalizationonNTU RGB+D
Accuracy (CS)· 2022-03-21
86
best: 94.3 (Hulk(Finetune, ViT-L))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Action LocalizationonNTU RGB+D
Accuracy (CV)· 2022-03-21
93.1
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Action LocalizationonNTU RGB+D
GFLOPs per pred· 2022-03-21
0.44
best: 16.73 (ST-GCN)
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009

Time Series16 results

Action DetectiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2022-03-21
82
best: 92.2 (ProtoGCN)
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Action DetectiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2022-03-21
80.4
best: 90.9 (ProtoGCN)
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Action DetectiononNTU RGB+D 120
GFLOPS per prediction· 2022-03-21
0.44
best: 37.38 (AGCN (2-stream))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Action DetectiononKinetics-Skeleton dataset
Accuracy· 2022-03-21
27.5
best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Action DetectiononKinetics-Skeleton dataset
GFLOPS per prediction· 2022-03-21
0.25
best: 26.91 (AGCN (2-stream))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Action DetectiononNTU RGB+D
Accuracy (CS)· 2022-03-21
86
best: 94.3 (Hulk(Finetune, ViT-L))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Action DetectiononNTU RGB+D
Accuracy (CV)· 2022-03-21
93.1
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Action DetectiononNTU RGB+D
GFLOPs per pred· 2022-03-21
0.44
best: 16.73 (ST-GCN)
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2022-03-21
82
best: 96.7 (DSCNet (RGB + Pose))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2022-03-21
80.4
best: 95.6 (DSCNet (RGB + Pose))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Action RecognitiononNTU RGB+D 120
GFLOPS per prediction· 2022-03-21
0.44
best: 37.38 (AGCN (2-stream))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Action RecognitiononKinetics-Skeleton dataset
Accuracy· 2022-03-21
27.5
best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Action RecognitiononKinetics-Skeleton dataset
GFLOPS per prediction· 2022-03-21
0.25
best: 26.91 (AGCN (2-stream))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Action RecognitiononNTU RGB+D
Accuracy (CS)· 2022-03-21
86
best: 97.4 (DSCNet (RGB + Pose))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Action RecognitiononNTU RGB+D
Accuracy (CV)· 2022-03-21
93.1
best: 99.6 (PoseC3D (RGB + Pose))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Action RecognitiononNTU RGB+D
GFLOPs per pred· 2022-03-21
0.44
best: 16.73 (ST-GCN)
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009

Methodology8 results

Zero-Shot LearningonNTU RGB+D 120
Accuracy (Cross-Setup)· 2022-03-21
82
best: 92.2 (ProtoGCN)
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Zero-Shot LearningonNTU RGB+D 120
Accuracy (Cross-Subject)· 2022-03-21
80.4
best: 90.9 (ProtoGCN)
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Zero-Shot LearningonNTU RGB+D 120
GFLOPS per prediction· 2022-03-21
0.44
best: 37.38 (AGCN (2-stream))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Zero-Shot LearningonKinetics-Skeleton dataset
Accuracy· 2022-03-21
27.5
best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Zero-Shot LearningonKinetics-Skeleton dataset
GFLOPS per prediction· 2022-03-21
0.25
best: 26.91 (AGCN (2-stream))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Zero-Shot LearningonNTU RGB+D
Accuracy (CS)· 2022-03-21
86
best: 94.3 (Hulk(Finetune, ViT-L))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Zero-Shot LearningonNTU RGB+D
Accuracy (CV)· 2022-03-21
93.1
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Zero-Shot LearningonNTU RGB+D
GFLOPs per pred· 2022-03-21
0.44
best: 16.73 (ST-GCN)
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009

Robots8 results

Activity RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2022-03-21
82
best: 96.7 (DSCNet (RGB + Pose))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Activity RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2022-03-21
80.4
best: 95.6 (DSCNet (RGB + Pose))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Activity RecognitiononNTU RGB+D 120
GFLOPS per prediction· 2022-03-21
0.44
best: 37.38 (AGCN (2-stream))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Activity RecognitiononKinetics-Skeleton dataset
Accuracy· 2022-03-21
27.5
best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Activity RecognitiononKinetics-Skeleton dataset
GFLOPS per prediction· 2022-03-21
0.25
best: 26.91 (AGCN (2-stream))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Activity RecognitiononNTU RGB+D
Accuracy (CS)· 2022-03-21
86
best: 97.4 (DSCNet (RGB + Pose))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Activity RecognitiononNTU RGB+D
Accuracy (CV)· 2022-03-21
93.1
best: 99.6 (PoseC3D (RGB + Pose))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
Activity RecognitiononNTU RGB+D
GFLOPs per pred· 2022-03-21
0.44
best: 16.73 (ST-GCN)
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009

Natural Language Processing8 results

3D Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2022-03-21
82
best: 92.2 (ProtoGCN)
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
3D Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2022-03-21
80.4
best: 90.9 (ProtoGCN)
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
3D Action RecognitiononNTU RGB+D 120
GFLOPS per prediction· 2022-03-21
0.44
best: 37.38 (AGCN (2-stream))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
3D Action RecognitiononKinetics-Skeleton dataset
Accuracy· 2022-03-21
27.5
best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
3D Action RecognitiononKinetics-Skeleton dataset
GFLOPS per prediction· 2022-03-21
0.25
best: 26.91 (AGCN (2-stream))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
3D Action RecognitiononNTU RGB+D
Accuracy (CS)· 2022-03-21
86
best: 94.3 (Hulk(Finetune, ViT-L))
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
3D Action RecognitiononNTU RGB+D
Accuracy (CV)· 2022-03-21
93.1
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009
3D Action RecognitiononNTU RGB+D
GFLOPs per pred· 2022-03-21
0.44
best: 16.73 (ST-GCN)
Continual Spatio-Temporal Graph Convolutional Networks arXiv:2203.11009