HyperAI초신경

Skeleton Based Action Recognition On Sbu

평가 지표

Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

		Paper Title
Joint Line Distance	99.02%	On Geometric Features for Skeleton-Based Action Recognition using Multilayer LSTM Networks
MLGCN	98.60%	MLGCN: Multi-Laplacian Graph Convolutional Networks for Human Action Recognition
VA-fusion (aug.)	98.3%	View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition
ArmaConv	96.00%	Graph Neural Networks with convolutional ARMA filters
ChebyNet	96.00%	Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
DeepGRU	95.7%	DeepGRU: Deep Gesture Recognition Utility
SGCConv	94.0%	Simplifying Graph Convolutional Networks
e2eET	93.96	Real-Time Hand Gesture Recognition: Integrating Skeleton-Based Data Fusion and Multi-Stream CNN
ST-LSTM + Trust Gate	93.3%	Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition

0 of 9 row(s) selected.

Skeleton Based Action Recognition On Sbu | SOTA | HyperAI초신경