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/TCA-GCN

TCA-GCN

Reported on 56 benchmarks across 8 tasks · 1 paper · 14 SOTA

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

Computer Vision21 results

VideoonNTU RGB+D 120
Accuracy (Cross-Subject)· 2022-05-31
89.4
best: 90.9 (ProtoGCN)
SOTA
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
VideoonN-UCLA
Accuracy· 2022-05-31
97
best: 99.1 (DSCNet (RGB + Pose))
SOTA
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Temporal Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Subject)· 2022-05-31
89.4
best: 90.9 (ProtoGCN)
SOTA
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Temporal Action LocalizationonN-UCLA
Accuracy· 2022-05-31
97
best: 99.1 (DSCNet (RGB + Pose))
SOTA
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Subject)· 2022-05-31
89.4
best: 90.9 (ProtoGCN)
SOTA
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Action LocalizationonN-UCLA
Accuracy· 2022-05-31
97
best: 99.1 (DSCNet (RGB + Pose))
SOTA
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
VideoonNTU RGB+D 120
Accuracy (Cross-Setup)· 2022-05-31
90.8
best: 92.2 (ProtoGCN)
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
VideoonNTU RGB+D 120
Ensembled Modalities· 2022-05-31
4
best: 6 (ProtoGCN)
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
VideoonNTU RGB+D
Accuracy (CS)· 2022-05-31
92.8
best: 94.3 (Hulk(Finetune, ViT-L))
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
VideoonNTU RGB+D
Accuracy (CV)· 2022-05-31
97
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
VideoonNTU RGB+D
Ensembled Modalities· 2022-05-31
4
best: 6 (ProtoGCN)
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Temporal Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Setup)· 2022-05-31
90.8
best: 92.2 (ProtoGCN)
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Temporal Action LocalizationonNTU RGB+D 120
Ensembled Modalities· 2022-05-31
4
best: 6 (ProtoGCN)
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Temporal Action LocalizationonNTU RGB+D
Accuracy (CS)· 2022-05-31
92.8
best: 94.3 (Hulk(Finetune, ViT-L))
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Temporal Action LocalizationonNTU RGB+D
Accuracy (CV)· 2022-05-31
97
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Temporal Action LocalizationonNTU RGB+D
Ensembled Modalities· 2022-05-31
4
best: 6 (ProtoGCN)
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Setup)· 2022-05-31
90.8
best: 92.2 (ProtoGCN)
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Action LocalizationonNTU RGB+D 120
Ensembled Modalities· 2022-05-31
4
best: 6 (ProtoGCN)
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Action LocalizationonNTU RGB+D
Accuracy (CS)· 2022-05-31
92.8
best: 94.3 (Hulk(Finetune, ViT-L))
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Action LocalizationonNTU RGB+D
Accuracy (CV)· 2022-05-31
97
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Action LocalizationonNTU RGB+D
Ensembled Modalities· 2022-05-31
4
best: 6 (ProtoGCN)
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936

Time Series14 results

Action DetectiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2022-05-31
89.4
best: 90.9 (ProtoGCN)
SOTA
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Action DetectiononN-UCLA
Accuracy· 2022-05-31
97
best: 99.1 (DSCNet (RGB + Pose))
SOTA
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Action RecognitiononN-UCLA
Accuracy· 2022-05-31
97
best: 99.1 (DSCNet (RGB + Pose))
SOTA
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Action DetectiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2022-05-31
90.8
best: 92.2 (ProtoGCN)
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Action DetectiononNTU RGB+D 120
Ensembled Modalities· 2022-05-31
4
best: 6 (ProtoGCN)
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Action DetectiononNTU RGB+D
Accuracy (CS)· 2022-05-31
92.8
best: 94.3 (Hulk(Finetune, ViT-L))
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Action DetectiononNTU RGB+D
Accuracy (CV)· 2022-05-31
97
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Action DetectiononNTU RGB+D
Ensembled Modalities· 2022-05-31
4
best: 6 (ProtoGCN)
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2022-05-31
90.8
best: 96.7 (DSCNet (RGB + Pose))
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2022-05-31
89.4
best: 95.6 (DSCNet (RGB + Pose))
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Action RecognitiononNTU RGB+D 120
Ensembled Modalities· 2022-05-31
4
best: 6 (ProtoGCN)
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Action RecognitiononNTU RGB+D
Accuracy (CS)· 2022-05-31
92.8
best: 97.4 (DSCNet (RGB + Pose))
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Action RecognitiononNTU RGB+D
Accuracy (CV)· 2022-05-31
97
best: 99.6 (PoseC3D (RGB + Pose))
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Action RecognitiononNTU RGB+D
Ensembled Modalities· 2022-05-31
4
best: 6 (ProtoGCN)
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936

Methodology7 results

Zero-Shot LearningonNTU RGB+D 120
Accuracy (Cross-Subject)· 2022-05-31
89.4
best: 90.9 (ProtoGCN)
SOTA
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Zero-Shot LearningonN-UCLA
Accuracy· 2022-05-31
97
best: 99.1 (DSCNet (RGB + Pose))
SOTA
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Zero-Shot LearningonNTU RGB+D 120
Accuracy (Cross-Setup)· 2022-05-31
90.8
best: 92.2 (ProtoGCN)
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Zero-Shot LearningonNTU RGB+D 120
Ensembled Modalities· 2022-05-31
4
best: 6 (ProtoGCN)
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Zero-Shot LearningonNTU RGB+D
Accuracy (CS)· 2022-05-31
92.8
best: 94.3 (Hulk(Finetune, ViT-L))
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Zero-Shot LearningonNTU RGB+D
Accuracy (CV)· 2022-05-31
97
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Zero-Shot LearningonNTU RGB+D
Ensembled Modalities· 2022-05-31
4
best: 6 (ProtoGCN)
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936

Robots7 results

Activity RecognitiononN-UCLA
Accuracy· 2022-05-31
97
best: 99.1 (DSCNet (RGB + Pose))
SOTA
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Activity RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2022-05-31
90.8
best: 96.7 (DSCNet (RGB + Pose))
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Activity RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2022-05-31
89.4
best: 95.6 (DSCNet (RGB + Pose))
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Activity RecognitiononNTU RGB+D 120
Ensembled Modalities· 2022-05-31
4
best: 6 (ProtoGCN)
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Activity RecognitiononNTU RGB+D
Accuracy (CS)· 2022-05-31
92.8
best: 97.4 (DSCNet (RGB + Pose))
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Activity RecognitiononNTU RGB+D
Accuracy (CV)· 2022-05-31
97
best: 99.6 (PoseC3D (RGB + Pose))
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
Activity RecognitiononNTU RGB+D
Ensembled Modalities· 2022-05-31
4
best: 6 (ProtoGCN)
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936

Natural Language Processing7 results

3D Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2022-05-31
89.4
best: 90.9 (ProtoGCN)
SOTA
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
3D Action RecognitiononN-UCLA
Accuracy· 2022-05-31
97
best: 99.1 (DSCNet (RGB + Pose))
SOTA
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
3D Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2022-05-31
90.8
best: 92.2 (ProtoGCN)
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
3D Action RecognitiononNTU RGB+D 120
Ensembled Modalities· 2022-05-31
4
best: 6 (ProtoGCN)
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
3D Action RecognitiononNTU RGB+D
Accuracy (CS)· 2022-05-31
92.8
best: 94.3 (Hulk(Finetune, ViT-L))
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
3D Action RecognitiononNTU RGB+D
Accuracy (CV)· 2022-05-31
97
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936
3D Action RecognitiononNTU RGB+D
Ensembled Modalities· 2022-05-31
4
best: 6 (ProtoGCN)
Skeleton-based Action Recognition via Temporal-Channel Aggregation arXiv:2205.15936