HyperAIHyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Skeleton Based Action Recognition On J Hmdb

Metrics

Accuracy (RGB+pose)
Accuracy (pose)

Results

Performance results of various models on this benchmark

Model Name
Accuracy (RGB+pose)
Accuracy (pose)
Paper TitleRepository
DD-Net-77.2Make Skeleton-based Action Recognition Model Smaller, Faster and Better-
Potion90.467.9PoTion: Pose MoTion Representation for Action Recognition-
MR Two-Sream R-CNN71.1-Multi-region two-stream R-CNN for action detection-
Action Tubes62.5-Finding Action Tubes-
RPAN83.9-RPAN: An End-to-End Recurrent Pose-Attention Network for Action Recognition in Videos-
EHPI-65.5Simple yet efficient real-time pose-based action recognition-
I3D + Potion85.5-PoTion: Pose MoTion Representation for Action Recognition-
I3D84.1-Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset-
PA3D69.5-PA3D: Pose-Action 3D Machine for Video Recognition-
STAR-Net64.3-STAR-Net: Action Recognition using Spatio-Temporal Activation Reprojection-
PA3D+RPAN86.1-PA3D: Pose-Action 3D Machine for Video Recognition-
Chained (RGB+Flow +Pose)76.156.8Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection-
0 of 12 row(s) selected.
Skeleton Based Action Recognition On J Hmdb | SOTA | HyperAI