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/GCN-NAS

GCN-NAS

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

VideoonKinetics-Skeleton dataset
Accuracy· 2019-11-11
37.1
best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
SOTA
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching arXiv:1911.04131
Temporal Action LocalizationonKinetics-Skeleton dataset
Accuracy· 2019-11-11
37.1
best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
SOTA
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching arXiv:1911.04131
Action LocalizationonKinetics-Skeleton dataset
Accuracy· 2019-11-11
37.1
best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
SOTA
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching arXiv:1911.04131
VideoonNTU RGB+D
Accuracy (CS)· 2019-11-11
89.4
best: 94.3 (Hulk(Finetune, ViT-L))
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching arXiv:1911.04131
VideoonNTU RGB+D
Accuracy (CV)· 2019-11-11
95.7
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching arXiv:1911.04131
Temporal Action LocalizationonNTU RGB+D
Accuracy (CS)· 2019-11-11
89.4
best: 94.3 (Hulk(Finetune, ViT-L))
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching arXiv:1911.04131
Temporal Action LocalizationonNTU RGB+D
Accuracy (CV)· 2019-11-11
95.7
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching arXiv:1911.04131
Action LocalizationonNTU RGB+D
Accuracy (CS)· 2019-11-11
89.4
best: 94.3 (Hulk(Finetune, ViT-L))
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching arXiv:1911.04131
Action LocalizationonNTU RGB+D
Accuracy (CV)· 2019-11-11
95.7
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching arXiv:1911.04131

Time Series6 results

Action DetectiononKinetics-Skeleton dataset
Accuracy· 2019-11-11
37.1
best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
SOTA
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching arXiv:1911.04131
Action RecognitiononKinetics-Skeleton dataset
Accuracy· 2019-11-11
37.1
best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
SOTA
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching arXiv:1911.04131
Action DetectiononNTU RGB+D
Accuracy (CS)· 2019-11-11
89.4
best: 94.3 (Hulk(Finetune, ViT-L))
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching arXiv:1911.04131
Action DetectiononNTU RGB+D
Accuracy (CV)· 2019-11-11
95.7
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching arXiv:1911.04131
Action RecognitiononNTU RGB+D
Accuracy (CS)· 2019-11-11
89.4
best: 97.4 (DSCNet (RGB + Pose))
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching arXiv:1911.04131
Action RecognitiononNTU RGB+D
Accuracy (CV)· 2019-11-11
95.7
best: 99.6 (PoseC3D (RGB + Pose))
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching arXiv:1911.04131

Methodology3 results

Zero-Shot LearningonKinetics-Skeleton dataset
Accuracy· 2019-11-11
37.1
best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
SOTA
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching arXiv:1911.04131
Zero-Shot LearningonNTU RGB+D
Accuracy (CS)· 2019-11-11
89.4
best: 94.3 (Hulk(Finetune, ViT-L))
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching arXiv:1911.04131
Zero-Shot LearningonNTU RGB+D
Accuracy (CV)· 2019-11-11
95.7
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching arXiv:1911.04131

Robots3 results

Activity RecognitiononKinetics-Skeleton dataset
Accuracy· 2019-11-11
37.1
best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
SOTA
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching arXiv:1911.04131
Activity RecognitiononNTU RGB+D
Accuracy (CS)· 2019-11-11
89.4
best: 97.4 (DSCNet (RGB + Pose))
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching arXiv:1911.04131
Activity RecognitiononNTU RGB+D
Accuracy (CV)· 2019-11-11
95.7
best: 99.6 (PoseC3D (RGB + Pose))
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching arXiv:1911.04131

Natural Language Processing3 results

3D Action RecognitiononKinetics-Skeleton dataset
Accuracy· 2019-11-11
37.1
best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
SOTA
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching arXiv:1911.04131
3D Action RecognitiononNTU RGB+D
Accuracy (CS)· 2019-11-11
89.4
best: 94.3 (Hulk(Finetune, ViT-L))
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching arXiv:1911.04131
3D Action RecognitiononNTU RGB+D
Accuracy (CV)· 2019-11-11
95.7
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching arXiv:1911.04131