HyperAI
HyperAI超神経
ホーム
プラットフォーム
ドキュメント
ニュース
論文
チュートリアル
データセット
百科事典
SOTA
LLMモデル
GPU ランキング
学会
検索
サイトについて
利用規約
プライバシーポリシー
日本語
HyperAI
HyperAI超神経
Toggle Sidebar
サイトを検索…
⌘
K
Command Palette
Search for a command to run...
プラットフォーム
ホーム
SOTA
骨格ベースの行動認識
Skeleton Based Action Recognition On N Ucla
Skeleton Based Action Recognition On N Ucla
評価指標
Accuracy
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
Columns
モデル名
Accuracy
Paper Title
DSCNet (RGB + Pose)
99.1
A Dense-Sparse Complementary Network for Human Action Recognition based on RGB and Skeleton Modalities
SkateFormer
98.3
SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition
LA-GCN
97.6
Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition
MMCL
97.5
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition
TD-GCN
97.4
Temporal Decoupling Graph Convolutional Network for Skeleton-based Gesture Recognition
Action Capsules
97.3
Action Capsules: Human Skeleton Action Recognition
HD-GCN
97.2
Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition
LST
97.2
Generative Action Description Prompts for Skeleton-based Action Recognition
InfoGCN
97.0
InfoGCN: Representation Learning for Human Skeleton-Based Action Recognition
TCA-GCN
97.0
Skeleton-based Action Recognition via Temporal-Channel Aggregation
CTR-GCN
96.5
Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition
TD-GDSCN
95.69
Action Recognition for Privacy-Preserving Ambient Assisted Living
MSSTNet
95.3
Multi-scale spatial–temporal convolutional neural network for skeleton-based action recognition
Hierarchical Action Classification (RGB + Pose)
93.99
Hierarchical Action Classification with Network Pruning
MMNet (RGB + Pose)
93.7
MMNet: A Model-Based Multimodal Network for Human Action Recognition in RGB-D Videos
VPN (RGB + Pose)
93.5
VPN: Learning Video-Pose Embedding for Activities of Daily Living
VPN++ (RGB + Pose)
93.5
VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living
SGN
92.5%
Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition
Action Machine
92.3%
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.
Previous
Next
Skeleton Based Action Recognition On N Ucla | SOTA | HyperAI超神経