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/3s-HYSP

3s-HYSP

Reported on 40 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 Vision15 results

VideoonPKU-MMD
Accuracy (Cross-Subject)· 2023-03-10
96.2
SOTA
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
Temporal Action LocalizationonPKU-MMD
Accuracy (Cross-Subject)· 2023-03-10
96.2
SOTA
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
Action LocalizationonPKU-MMD
Accuracy (Cross-Subject)· 2023-03-10
96.2
SOTA
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
VideoonNTU RGB+D 120
Accuracy (Cross-Setup)· 2023-03-10
86.3
best: 92.2 (ProtoGCN)
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
VideoonNTU RGB+D 120
Accuracy (Cross-Subject)· 2023-03-10
84.5
best: 90.9 (ProtoGCN)
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
VideoonNTU RGB+D
Accuracy (CS)· 2023-03-10
89.1
best: 94.3 (Hulk(Finetune, ViT-L))
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
VideoonNTU RGB+D
Accuracy (CV)· 2023-03-10
95.2
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
Temporal Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Setup)· 2023-03-10
86.3
best: 92.2 (ProtoGCN)
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
Temporal Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Subject)· 2023-03-10
84.5
best: 90.9 (ProtoGCN)
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
Temporal Action LocalizationonNTU RGB+D
Accuracy (CS)· 2023-03-10
89.1
best: 94.3 (Hulk(Finetune, ViT-L))
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
Temporal Action LocalizationonNTU RGB+D
Accuracy (CV)· 2023-03-10
95.2
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Setup)· 2023-03-10
86.3
best: 92.2 (ProtoGCN)
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Subject)· 2023-03-10
84.5
best: 90.9 (ProtoGCN)
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
Action LocalizationonNTU RGB+D
Accuracy (CS)· 2023-03-10
89.1
best: 94.3 (Hulk(Finetune, ViT-L))
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
Action LocalizationonNTU RGB+D
Accuracy (CV)· 2023-03-10
95.2
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242

Time Series10 results

Action DetectiononPKU-MMD
Accuracy (Cross-Subject)· 2023-03-10
96.2
SOTA
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
Action RecognitiononPKU-MMD
Accuracy (Cross-Subject)· 2023-03-10
96.2
SOTA
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
Action DetectiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2023-03-10
86.3
best: 92.2 (ProtoGCN)
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
Action DetectiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2023-03-10
84.5
best: 90.9 (ProtoGCN)
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
Action DetectiononNTU RGB+D
Accuracy (CS)· 2023-03-10
89.1
best: 94.3 (Hulk(Finetune, ViT-L))
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
Action DetectiononNTU RGB+D
Accuracy (CV)· 2023-03-10
95.2
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2023-03-10
86.3
best: 96.7 (DSCNet (RGB + Pose))
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2023-03-10
84.5
best: 95.6 (DSCNet (RGB + Pose))
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
Action RecognitiononNTU RGB+D
Accuracy (CS)· 2023-03-10
89.1
best: 97.4 (DSCNet (RGB + Pose))
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
Action RecognitiononNTU RGB+D
Accuracy (CV)· 2023-03-10
95.2
best: 99.6 (PoseC3D (RGB + Pose))
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242

Methodology5 results

Zero-Shot LearningonPKU-MMD
Accuracy (Cross-Subject)· 2023-03-10
96.2
SOTA
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
Zero-Shot LearningonNTU RGB+D 120
Accuracy (Cross-Setup)· 2023-03-10
86.3
best: 92.2 (ProtoGCN)
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
Zero-Shot LearningonNTU RGB+D 120
Accuracy (Cross-Subject)· 2023-03-10
84.5
best: 90.9 (ProtoGCN)
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
Zero-Shot LearningonNTU RGB+D
Accuracy (CS)· 2023-03-10
89.1
best: 94.3 (Hulk(Finetune, ViT-L))
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
Zero-Shot LearningonNTU RGB+D
Accuracy (CV)· 2023-03-10
95.2
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242

Robots5 results

Activity RecognitiononPKU-MMD
Accuracy (Cross-Subject)· 2023-03-10
96.2
SOTA
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
Activity RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2023-03-10
86.3
best: 96.7 (DSCNet (RGB + Pose))
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
Activity RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2023-03-10
84.5
best: 95.6 (DSCNet (RGB + Pose))
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
Activity RecognitiononNTU RGB+D
Accuracy (CS)· 2023-03-10
89.1
best: 97.4 (DSCNet (RGB + Pose))
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
Activity RecognitiononNTU RGB+D
Accuracy (CV)· 2023-03-10
95.2
best: 99.6 (PoseC3D (RGB + Pose))
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242

Natural Language Processing5 results

3D Action RecognitiononPKU-MMD
Accuracy (Cross-Subject)· 2023-03-10
96.2
SOTA
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
3D Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2023-03-10
86.3
best: 92.2 (ProtoGCN)
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
3D Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2023-03-10
84.5
best: 90.9 (ProtoGCN)
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
3D Action RecognitiononNTU RGB+D
Accuracy (CS)· 2023-03-10
89.1
best: 94.3 (Hulk(Finetune, ViT-L))
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242
3D Action RecognitiononNTU RGB+D
Accuracy (CV)· 2023-03-10
95.2
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations arXiv:2303.06242