HyperAI
HyperAI
Home
Console
Docs
News
Papers
Tutorials
Datasets
Wiki
SOTA
LLM Models
GPU Leaderboard
Events
Search
About
Terms of Service
Privacy Policy
English
HyperAI
HyperAI
Toggle Sidebar
Search the site…
⌘
K
Command Palette
Search for a command to run...
Console
Home
SOTA
Skeleton Based Action Recognition
Skeleton Based Action Recognition On Ntu Rgbd
Skeleton Based Action Recognition On Ntu Rgbd
Metrics
Accuracy (CS)
Accuracy (CV)
Results
Performance results of various models on this benchmark
Columns
Model Name
Accuracy (CS)
Accuracy (CV)
Paper Title
Lit-llama
95
98.4
LLMs are Good Action Recognizers
Hulk(Finetune, ViT-L)
94.3
-
Hulk: A Universal Knowledge Translator for Human-Centric Tasks
PoseC3D [3D Heatmap]
94.1
97.1
Revisiting Skeleton-based Action Recognition
Hulk(Finetune, ViT-B)
94
-
Hulk: A Universal Knowledge Translator for Human-Centric Tasks
MaskCLR
93.9
97.3
MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning
ProtoGCN
93.8
97.8
Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition
Shap-Mix
93.7
97.1
Shap-Mix: Shapley Value Guided Mixing for Long-Tailed Skeleton Based Action Recognition
JMDA (based on Skeleton MixFormer)
93.7
97.2
Joint Mixing Data Augmentation for Skeleton-based Action Recognition
DeGCN
93.6
97.4
DeGCN: Deformable Graph Convolutional Networks for Skeleton-Based Action Recognition
MSA-GCN
93.6
97.4
MSA-GCN: Exploiting Multi-Scale Temporal Dynamics With Adaptive Graph Convolution for Skeleton-Based Action Recognition
SkateFormer
93.5
97.8
SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition
LA-GCN
93.5
97.2
Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition
MMCL
93.5
97.4
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition
HD-GCN
93.4
97.2
Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition
STEP-CATFormer
93.2
97.3
STEP CATFormer: Spatial-Temporal Effective Body-Part Cross Attention Transformer for Skeleton-based Action Recognition
DG-STGCN
93.2
97.5
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition
SkeletonGCL (based on CTR-GCN)
93.1
97.0
Graph Contrastive Learning for Skeleton-based Action Recognition
MAMP
93.1
97.5
Masked Motion Predictors are Strong 3D Action Representation Learners
BlockGCN
93.1
97.0
BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition
MotionBert (finetune)
93.0
97.2
MotionBERT: A Unified Perspective on Learning Human Motion Representations
0 of 133 row(s) selected.
Previous
Next
Skeleton Based Action Recognition On Ntu Rgbd | SOTA | HyperAI