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/DSTSA-GCN

DSTSA-GCN

Reported on 76 benchmarks across 10 tasks · 1 paper · 18 SOTA

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

Computer Vision31 results

VideoonSHREC 2017 track on 3D Hand Gesture Recognition
14 gestures accuracy· 2025-01-21
97.74
best: 99.85 (RE-TCN)
SOTA
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
VideoonSHREC 2017 track on 3D Hand Gesture Recognition
28 gestures accuracy· 2025-01-21
95.37
best: 99.95 (RE-TCN)
SOTA
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Temporal Action LocalizationonSHREC 2017 track on 3D Hand Gesture Recognition
14 gestures accuracy· 2025-01-21
97.74
best: 99.85 (RE-TCN)
SOTA
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Temporal Action LocalizationonSHREC 2017 track on 3D Hand Gesture Recognition
28 gestures accuracy· 2025-01-21
95.37
best: 99.95 (RE-TCN)
SOTA
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action LocalizationonSHREC 2017 track on 3D Hand Gesture Recognition
14 gestures accuracy· 2025-01-21
97.74
best: 99.85 (RE-TCN)
SOTA
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action LocalizationonSHREC 2017 track on 3D Hand Gesture Recognition
28 gestures accuracy· 2025-01-21
95.37
best: 99.95 (RE-TCN)
SOTA
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
HandonDHG-28
Accuracy· 2025-01-21
93.57
SOTA
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Gesture RecognitiononDHG-28
Accuracy· 2025-01-21
93.57
SOTA
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
VideoonNTU RGB+D 120
Accuracy (Cross-Setup)· 2025-01-21
90.97
best: 92.2 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
VideoonNTU RGB+D 120
Accuracy (Cross-Subject)· 2025-01-21
89.12
best: 90.9 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
VideoonNTU RGB+D 120
Ensembled Modalities· 2025-01-21
4
best: 6 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
VideoonN-UCLA
Accuracy· 2025-01-21
96.98
best: 99.1 (DSCNet (RGB + Pose))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
VideoonNTU RGB+D
Accuracy (CS)· 2025-01-21
92.78
best: 94.3 (Hulk(Finetune, ViT-L))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
VideoonNTU RGB+D
Accuracy (CV)· 2025-01-21
97.03
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
VideoonNTU RGB+D
Ensembled Modalities· 2025-01-21
4
best: 6 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Temporal Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Setup)· 2025-01-21
90.97
best: 92.2 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Temporal Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Subject)· 2025-01-21
89.12
best: 90.9 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Temporal Action LocalizationonNTU RGB+D 120
Ensembled Modalities· 2025-01-21
4
best: 6 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Temporal Action LocalizationonN-UCLA
Accuracy· 2025-01-21
96.98
best: 99.1 (DSCNet (RGB + Pose))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Temporal Action LocalizationonNTU RGB+D
Accuracy (CS)· 2025-01-21
92.78
best: 94.3 (Hulk(Finetune, ViT-L))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Temporal Action LocalizationonNTU RGB+D
Accuracy (CV)· 2025-01-21
97.03
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Temporal Action LocalizationonNTU RGB+D
Ensembled Modalities· 2025-01-21
4
best: 6 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Setup)· 2025-01-21
90.97
best: 92.2 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Subject)· 2025-01-21
89.12
best: 90.9 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action LocalizationonNTU RGB+D 120
Ensembled Modalities· 2025-01-21
4
best: 6 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action LocalizationonN-UCLA
Accuracy· 2025-01-21
96.98
best: 99.1 (DSCNet (RGB + Pose))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action LocalizationonNTU RGB+D
Accuracy (CS)· 2025-01-21
92.78
best: 94.3 (Hulk(Finetune, ViT-L))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action LocalizationonNTU RGB+D
Accuracy (CV)· 2025-01-21
97.03
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action LocalizationonNTU RGB+D
Ensembled Modalities· 2025-01-21
4
best: 6 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
HandonDHG-14
Accuracy· 2025-01-21
95.04
best: 95.83 (e2eET)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Gesture RecognitiononDHG-14
Accuracy· 2025-01-21
95.04
best: 95.83 (e2eET)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086

Time Series22 results

Action DetectiononSHREC 2017 track on 3D Hand Gesture Recognition
14 gestures accuracy· 2025-01-21
97.74
best: 99.85 (RE-TCN)
SOTA
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action DetectiononSHREC 2017 track on 3D Hand Gesture Recognition
28 gestures accuracy· 2025-01-21
95.37
best: 99.95 (RE-TCN)
SOTA
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action RecognitiononSHREC 2017 track on 3D Hand Gesture Recognition
14 gestures accuracy· 2025-01-21
97.74
best: 99.85 (RE-TCN)
SOTA
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action RecognitiononSHREC 2017 track on 3D Hand Gesture Recognition
28 gestures accuracy· 2025-01-21
95.37
best: 99.95 (RE-TCN)
SOTA
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action DetectiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2025-01-21
90.97
best: 92.2 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action DetectiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2025-01-21
89.12
best: 90.9 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action DetectiononNTU RGB+D 120
Ensembled Modalities· 2025-01-21
4
best: 6 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action DetectiononN-UCLA
Accuracy· 2025-01-21
96.98
best: 99.1 (DSCNet (RGB + Pose))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action DetectiononNTU RGB+D
Accuracy (CS)· 2025-01-21
92.78
best: 94.3 (Hulk(Finetune, ViT-L))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action DetectiononNTU RGB+D
Accuracy (CV)· 2025-01-21
97.03
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action DetectiononNTU RGB+D
Ensembled Modalities· 2025-01-21
4
best: 6 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action RecognitiononNTU RGB+D
Accuracy (CS)· 2025-01-21
92.78
best: 97.4 (DSCNet (RGB + Pose))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action RecognitiononNTU RGB+D
Accuracy (CV)· 2025-01-21
97.03
best: 99.6 (PoseC3D (RGB + Pose))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2025-01-21
90.97
best: 96.7 (DSCNet (RGB + Pose))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2025-01-21
89.12
best: 95.6 (DSCNet (RGB + Pose))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2025-01-21
90.97
best: 96.7 (DSCNet (RGB + Pose))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2025-01-21
89.12
best: 95.6 (DSCNet (RGB + Pose))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action RecognitiononNTU RGB+D 120
Ensembled Modalities· 2025-01-21
4
best: 6 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action RecognitiononN-UCLA
Accuracy· 2025-01-21
96.98
best: 99.1 (DSCNet (RGB + Pose))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action RecognitiononNTU RGB+D
Accuracy (CS)· 2025-01-21
92.78
best: 97.4 (DSCNet (RGB + Pose))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action RecognitiononNTU RGB+D
Accuracy (CV)· 2025-01-21
97.03
best: 99.6 (PoseC3D (RGB + Pose))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Action RecognitiononNTU RGB+D
Ensembled Modalities· 2025-01-21
4
best: 6 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086

Robots13 results

Activity RecognitiononSHREC 2017 track on 3D Hand Gesture Recognition
14 gestures accuracy· 2025-01-21
97.74
best: 99.85 (RE-TCN)
SOTA
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Activity RecognitiononSHREC 2017 track on 3D Hand Gesture Recognition
28 gestures accuracy· 2025-01-21
95.37
best: 99.95 (RE-TCN)
SOTA
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Activity RecognitiononNTU RGB+D
Accuracy (CS)· 2025-01-21
92.78
best: 97.4 (DSCNet (RGB + Pose))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Activity RecognitiononNTU RGB+D
Accuracy (CV)· 2025-01-21
97.03
best: 99.6 (PoseC3D (RGB + Pose))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Activity RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2025-01-21
90.97
best: 96.7 (DSCNet (RGB + Pose))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Activity RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2025-01-21
89.12
best: 95.6 (DSCNet (RGB + Pose))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Activity RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2025-01-21
90.97
best: 96.7 (DSCNet (RGB + Pose))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Activity RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2025-01-21
89.12
best: 95.6 (DSCNet (RGB + Pose))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Activity RecognitiononNTU RGB+D 120
Ensembled Modalities· 2025-01-21
4
best: 6 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Activity RecognitiononN-UCLA
Accuracy· 2025-01-21
96.98
best: 99.1 (DSCNet (RGB + Pose))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Activity RecognitiononNTU RGB+D
Accuracy (CS)· 2025-01-21
92.78
best: 97.4 (DSCNet (RGB + Pose))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Activity RecognitiononNTU RGB+D
Accuracy (CV)· 2025-01-21
97.03
best: 99.6 (PoseC3D (RGB + Pose))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Activity RecognitiononNTU RGB+D
Ensembled Modalities· 2025-01-21
4
best: 6 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086

Methodology9 results

Zero-Shot LearningonSHREC 2017 track on 3D Hand Gesture Recognition
14 gestures accuracy· 2025-01-21
97.74
best: 99.85 (RE-TCN)
SOTA
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Zero-Shot LearningonSHREC 2017 track on 3D Hand Gesture Recognition
28 gestures accuracy· 2025-01-21
95.37
best: 99.95 (RE-TCN)
SOTA
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Zero-Shot LearningonNTU RGB+D 120
Accuracy (Cross-Setup)· 2025-01-21
90.97
best: 92.2 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Zero-Shot LearningonNTU RGB+D 120
Accuracy (Cross-Subject)· 2025-01-21
89.12
best: 90.9 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Zero-Shot LearningonNTU RGB+D 120
Ensembled Modalities· 2025-01-21
4
best: 6 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Zero-Shot LearningonN-UCLA
Accuracy· 2025-01-21
96.98
best: 99.1 (DSCNet (RGB + Pose))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Zero-Shot LearningonNTU RGB+D
Accuracy (CS)· 2025-01-21
92.78
best: 94.3 (Hulk(Finetune, ViT-L))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Zero-Shot LearningonNTU RGB+D
Accuracy (CV)· 2025-01-21
97.03
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
Zero-Shot LearningonNTU RGB+D
Ensembled Modalities· 2025-01-21
4
best: 6 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086

Natural Language Processing9 results

3D Action RecognitiononSHREC 2017 track on 3D Hand Gesture Recognition
14 gestures accuracy· 2025-01-21
97.74
best: 99.85 (RE-TCN)
SOTA
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
3D Action RecognitiononSHREC 2017 track on 3D Hand Gesture Recognition
28 gestures accuracy· 2025-01-21
95.37
best: 99.95 (RE-TCN)
SOTA
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
3D Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2025-01-21
90.97
best: 92.2 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
3D Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2025-01-21
89.12
best: 90.9 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
3D Action RecognitiononNTU RGB+D 120
Ensembled Modalities· 2025-01-21
4
best: 6 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
3D Action RecognitiononN-UCLA
Accuracy· 2025-01-21
96.98
best: 99.1 (DSCNet (RGB + Pose))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
3D Action RecognitiononNTU RGB+D
Accuracy (CS)· 2025-01-21
92.78
best: 94.3 (Hulk(Finetune, ViT-L))
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
3D Action RecognitiononNTU RGB+D
Accuracy (CV)· 2025-01-21
97.03
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086
3D Action RecognitiononNTU RGB+D
Ensembled Modalities· 2025-01-21
4
best: 6 (ProtoGCN)
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling arXiv:2501.12086