Action Classification On Toyota Smarthome

Metrics

CS

CV1

CV2

Results

Performance results of various models on this benchmark

				Paper Title
π-ViT	72.9	55.2	64.8	Just Add $\pi$! Pose Induced Video Transformers for Understanding Activities of Daily Living
MMNet	70.1	-	-	MMNet: A Model-Based Multimodal Network for Human Action Recognition in RGB-D Videos
UNIK	64.3	36.1	65.0	UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition
AssembleNet++	63.6	-	-	AssembleNet++: Assembling Modality Representations via Attention Connections
AIRStreams	62.11	-	-	Adaptive Intermediate Representations for Video Understanding
VPN (RGB + Pose)	60.8	43.8	53.5	VPN: Learning Video-Pose Embedding for Activities of Daily Living
Separable STA (RGB + Pose)	54.2	35.2	50.3	Toyota Smarthome: Real-World Activities of Daily Living
I3D + Non Local	53.6	34.3	43.9	Non-local Neural Networks
I3D	53.4	34.9	45.1	Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
Dense Trajectories	41.9	20.9	23.7	Improved Dense Trajectory with Cross Streams
NPL	-	39.6	54.6	Recognizing Actions in Videos from Unseen Viewpoints
Trans4SOAR (Pose)	-	-	-	Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions

0 of 12 row(s) selected.

Action Classification On Toyota Smarthome | SOTA | HyperAI