DECA: Deep viewpoint-Equivariant human pose estimation using Capsule Autoencoders

Open paper

Benchmark	Model	Rank	Results
pose-estimation-on-itop-front-view	DECA-D3	#3	Mean mAP: 88.75
pose-estimation-on-itop-top-view	DECA-D3	#1	Mean mAP: 86.92
pose-estimation-on-itop-top-view	DECA-D3	#2	Mean mAP: 86.92