Skeleton Based Action Recognition On N Ucla

Métriques

Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	Accuracy	Paper Title	Repository
SGN	92.5%	Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition
HD-GCN	97.2	Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition
InfoGCN	97.0	InfoGCN: Representation Learning for Human Skeleton-Based Action Recognition
MMNet (RGB + Pose)	93.7	MMNet: A Model-Based Multimodal Network for Human Action Recognition in RGB-D Videos
VPN (RGB + Pose)	93.5	VPN: Learning Video-Pose Embedding for Activities of Daily Living
SkateFormer	98.3	SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition
VPN++ (RGB + Pose)	93.5	VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living
LA-GCN	97.6	Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition
TCA-GCN	97.0	Skeleton-based Action Recognition via Temporal-Channel Aggregation
TD-GDSCN	95.69	Action Recognition for Privacy-Preserving Ambient Assisted Living
Action Capsules	97.3	Action Capsules: Human Skeleton Action Recognition	-
MSSTNet	95.3	Multi-scale spatial–temporal convolutional neural network for skeleton-based action recognition
VA-fusion (aug.)	88.1%	View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition
Hierarchical Action Classification (RGB + Pose)	93.99	Hierarchical Action Classification with Network Pruning	-
CTR-GCN	96.5	Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition
TD-GCN	97.4	Temporal Decoupling Graph Convolutional Network for Skeleton-based Gesture Recognition	-
Action Machine	92.3%	Action Machine: Rethinking Action Recognition in Trimmed Videos	-
Glimpse Clouds	87.6%	Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points
MMCL	97.5	Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition
LST	97.2	Generative Action Description Prompts for Skeleton-based Action Recognition

0 of 22 row(s) selected.