HyperAI超神経
ホームニュース最新論文チュートリアルデータセット百科事典SOTALLMモデルGPU ランキング学会
検索
サイトについて
HyperAI超神経

Action Recognition In Videos On Ntu Rgbd

評価指標

Accuracy (CS)
Accuracy (CV)

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

モデル名
Accuracy (CS)
Accuracy (CV)
Paper TitleRepository
MMNet (RGB + Pose)96.098.8MMNet: A Model-Based Multimodal Network for Human Action Recognition in RGB-D Videos
FUSION (IR+Pose)91.894.9Infrared and 3D skeleton feature fusion for RGB-D action recognition
VPN (RGB + Pose)95.598.0VPN: Learning Video-Pose Embedding for Activities of Daily Living
STAR-Transformer (RGB + Pose)92.096.5STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition-
PoseC3D (RGB + Pose)97.099.6Revisiting Skeleton-based Action Recognition
ViewCon (RGB + Pose)93.798.9Multi-View Action Recognition Using Contrastive Learning
DVANet (RGB only)93.498.1DVANet: Disentangling View and Action Features for Multi-View Action Recognition
3DA (RGB + Pose)94.397.9Cross-Modal Learning with 3D Deformable Attention for Action Recognition-
PoseMap (RGB+Pose)91.795.2Recognizing Human Actions as the Evolution of Pose Estimation Maps-
PB-GCN (Skeleton only)87.593.2Part-based Graph Convolutional Network for Action Recognition
DSSCA-SSLM (RGB only)74.9-Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videos-
UMDR (RGB-D)96.298.0A Unified Multimodal De- and Re-coupling Framework for RGB-D Motion Recognition
DSCNet (RGB + Pose)97.499.4A Dense-Sparse Complementary Network for Human Action Recognition based on RGB and Skeleton Modalities
TSMF (RGB + Pose)92.597.4Multimodal Fusion via Teacher-Student Network for Indoor Action Recognition
π-ViT (RGB + Pose)96.399.0Just Add $π$! Pose Induced Video Transformers for Understanding Activities of Daily Living
Glimpse Clouds (RGB only)86.693.2Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points
MMTM (RGB+Pose)91.99-MMTM: Multimodal Transfer Module for CNN Fusion
B2C-AFM(RGB+Pose)91.7-B2C-AFM: Bi-Directional Co-Temporal and Cross-Spatial Attention Fusion Model for Human Action Recognition
EPP-Net (Parsing + Pose)94.797.7Explore Human Parsing Modality for Action Recognition
Hierarchical Action Classification (RGB + Pose)95.6698.79Hierarchical Action Classification with Network Pruning-
0 of 25 row(s) selected.