HyperAI超神经
首页资讯最新论文教程数据集百科SOTALLM 模型天梯GPU 天梯顶会
全站搜索
关于
HyperAI超神经

Skeleton Based Action Recognition On Kinetics

评估指标

Accuracy

评测结果

各个模型在此基准测试上的表现结果

模型名称
Accuracy
Paper TitleRepository
ProtoGCN51.9Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition
ST-TR-agcn37.4Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks
ST-GCN (2-stream)34.4Continual Spatio-Temporal Graph Convolutional Networks
CGCN37.5Unifying Graph Embedding Features with Graph Convolutional Networks for Skeleton-based Action Recognition-
CoST-GCN* (1-stream)30.2Continual Spatio-Temporal Graph Convolutional Networks
Structured Keypoint Pooling (PPNv2 skeletons+objects)52.3Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling-
CoAGCN* (1-stream)23.3Continual Spatio-Temporal Graph Convolutional Networks
SLnL-rFA36.6Skeleton-Based Action Recognition with Synchronous Local and Non-local Spatio-temporal Learning and Frequency Attention-
ST-GR33.6Spatiotemporal graph routing for skeleton-based action recognition-
DualHead-Net38.4Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition
Dynamic GCN37.9Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognition
CoST-GCN* (2-stream)32.2Continual Spatio-Temporal Graph Convolutional Networks
MS-G3D38.0Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition
JB-AAGCN37.4Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks
AS-GCN34.8Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition
DGNN36.9Skeleton-Based Action Recognition With Directed Graph Neural Networks-
CoS-TR* (1-stream)27.4Continual Spatio-Temporal Graph Convolutional Networks
CoAGCN (1-stream)33Continual Spatio-Temporal Graph Convolutional Networks
2s-AGCN+TEM38.6Temporal Extension Module for Skeleton-Based Action Recognition-
HD-GCN40.9Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition
0 of 42 row(s) selected.