Skeleton Based Action Recognition On J Hmdb

Metrics

Accuracy (RGB+pose)

Accuracy (pose)

Results

Performance results of various models on this benchmark

			Paper Title
Potion	90.4	67.9	PoTion: Pose MoTion Representation for Action Recognition
PA3D+RPAN	86.1	-	PA3D: Pose-Action 3D Machine for Video Recognition
I3D + Potion	85.5	-	PoTion: Pose MoTion Representation for Action Recognition
I3D	84.1	-	Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
RPAN	83.9	-	RPAN: An End-to-End Recurrent Pose-Attention Network for Action Recognition in Videos
Chained (RGB+Flow +Pose)	76.1	56.8	Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection
MR Two-Sream R-CNN	71.1	-	Multi-region two-stream R-CNN for action detection
PA3D	69.5	-	PA3D: Pose-Action 3D Machine for Video Recognition
STAR-Net	64.3	-	STAR-Net: Action Recognition using Spatio-Temporal Activation Reprojection
Action Tubes	62.5	-	Finding Action Tubes
DD-Net	-	77.2	Make Skeleton-based Action Recognition Model Smaller, Faster and Better
EHPI	-	65.5	Simple yet efficient real-time pose-based action recognition

0 of 12 row(s) selected.

Skeleton Based Action Recognition On J Hmdb | SOTA | HyperAI