HyperAIHyperAI
HomeConsoleDocsNewsPapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Command Palette

Search for a command to run...

Skeleton Based Action Recognition On N Ucla

Metrics

Accuracy

Results

Performance results of various models on this benchmark

Paper TitleRepository
DSCNet (RGB + Pose)99.1A Dense-Sparse Complementary Network for Human Action Recognition based on RGB and Skeleton Modalities-
SkateFormer98.3SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition
LA-GCN97.6Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition
MMCL97.5Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition
TD-GCN97.4Temporal Decoupling Graph Convolutional Network for Skeleton-based Gesture Recognition-
Action Capsules97.3Action Capsules: Human Skeleton Action Recognition-
HD-GCN97.2Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition
LST97.2Generative Action Description Prompts for Skeleton-based Action Recognition
InfoGCN97.0InfoGCN: Representation Learning for Human Skeleton-Based Action Recognition-
TCA-GCN97.0Skeleton-based Action Recognition via Temporal-Channel Aggregation
CTR-GCN96.5Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition
TD-GDSCN95.69Action Recognition for Privacy-Preserving Ambient Assisted Living-
MSSTNet95.3Multi-scale spatial–temporal convolutional neural network for skeleton-based action recognition-
Hierarchical Action Classification (RGB + Pose)93.99Hierarchical Action Classification with Network Pruning-
MMNet (RGB + Pose)93.7MMNet: A Model-Based Multimodal Network for Human Action Recognition in RGB-D Videos-
VPN (RGB + Pose)93.5VPN: Learning Video-Pose Embedding for Activities of Daily Living
VPN++ (RGB + Pose)93.5VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living
SGN92.5%Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition
Action Machine92.3%Action Machine: Rethinking Action Recognition in Trimmed Videos-
EleAtt-GRU (aug.)90.7%EleAtt-RNN: Adding Attentiveness to Neurons in Recurrent Neural Networks-
0 of 22 row(s) selected.
Skeleton Based Action Recognition On N Ucla | SOTA | HyperAI