HyperAIHyperAI
HomeConsoleDocsNewsPapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Command Palette

Search for a command to run...

Skeleton Based Action Recognition On Kinetics

Metrics

Accuracy

Results

Performance results of various models on this benchmark

Paper TitleRepository
Structured Keypoint Pooling (PPNv2 skeletons+objects)52.3Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling-
ProtoGCN51.9Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition
Structured Keypoint Pooling (HRNet skeletons)50.3Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling-
PoseC3D (SlowOnly-346)49.1Revisiting Skeleton-based Action Recognition
PoseC3D47.7Revisiting Skeleton-based Action Recognition
Structured Keypoint Pooling (PPNv2 skeletons)43.1Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling-
HD-GCN40.9Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition
2s-AGCN+TEM38.6Temporal Extension Module for Skeleton-Based Action Recognition-
DualHead-Net38.4Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition
MS-G3D38.0Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition
Dynamic GCN37.9Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognition
MS-AAGCN37.8Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks
CGCN37.5Unifying Graph Embedding Features with Graph Convolutional Networks for Skeleton-based Action Recognition-
ST-TR-agcn37.4Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks
JB-AAGCN37.4Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks
GCN-NAS37.1Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching
DGNN36.9Skeleton-Based Action Recognition With Directed Graph Neural Networks-
AGCN (2-stream)36.9Continual Spatio-Temporal Graph Convolutional Networks
SLnL-rFA36.6Skeleton-Based Action Recognition with Synchronous Local and Non-local Spatio-temporal Learning and Frequency Attention-
AGCN (1-stream)35Continual Spatio-Temporal Graph Convolutional Networks
0 of 42 row(s) selected.
Skeleton Based Action Recognition On Kinetics | SOTA | HyperAI