Skeleton Based Action Recognition On Ntu Rgbd 1

评估指标

Accuracy (Cross-Setup)

Accuracy (Cross-Subject)

GFLOPS per prediction

评测结果

各个模型在此基准测试上的表现结果

				Paper Title	Repository
DeGCN	92.1	91.0	-	DeGCN: Deformable Graph Convolutional Networks for Skeleton-Based Action Recognition	-
JMDA (based on Skeleton MixFormer)	91.9	90.9	-	Joint Mixing Data Augmentation for Skeleton-based Action Recognition	-
ProtoGCN	92.2	90.9	-	Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition
LA-GCN	91.8	90.7	-	Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition
Shap-Mix	91.7	90.4	-	Shap-Mix: Shapley Value Guided Mixing for Long-Tailed Skeleton Based Action Recognition
BlockGCN	91.5	90.3	-	BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition	-
MMCL	91.7	90.3	-	Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition
TSGCNeXt	91.7	90.2	-	TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential
HD-GCN	91.6	90.1	-	Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition
STEP-CATFormer	91.2	90.0	-	STEP CATFormer: Spatial-Temporal Effective Body-Part Cross Attention Transformer for Skeleton-based Action Recognition
MAMP	91.3	90.0	-	Masked Motion Predictors are Strong 3D Action Representation Learners
Hyperformer	91.3	89.9	-	Hypergraph Transformer for Skeleton-based Action Recognition
LST	91.1	89.9	-	Generative Action Description Prompts for Skeleton-based Action Recognition
SkateFormer	91.4	89.8	-	SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition
InfoGCN	91.2	89.8	-	InfoGCN: Representation Learning for Human Skeleton-Based Action Recognition	-
Stream-GCN	91.0	89.7	-	Action Recognition with Multi-stream Motion Modeling and Mutual Information Maximization	-
DG-STGCN	91.3	89.6	-	DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition
SkeletonGCL (based on CTR-GCN)	91.0	89.5	-	Graph Contrastive Learning for Skeleton-based Action Recognition
TCA-GCN	90.8	89.4	-	Skeleton-based Action Recognition via Temporal-Channel Aggregation
PSUMNet	90.6	89.4	-	PSUMNet: Unified Modality Part Streams are All You Need for Efficient Pose-based Action Recognition

0 of 81 row(s) selected.

Command Palette

Skeleton Based Action Recognition On Ntu Rgbd 1

评估指标

评测结果