Multi Person Pose Estimation On Coco

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

		Paper Title
RSN	0.792	Learning Delicate Local Representations for Multi-Person Pose Estimation
DarkPose	0.774	Distribution-Aware Coordinate Representation for Human Pose Estimation
UniPose	0.768	X-Pose: Detecting Any Keypoints
CPN+	0.730	Cascaded Pyramid Network for Multi-Person Pose Estimation
BAPose	0.727	BAPose: Bottom-Up Pose Estimation with Disentangled Waterfall Representations
CenterGroup	0.714	The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimation
OpenPifPaf	0.709	OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association
Pose Residual Network	0.697	MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network
G-RMI*	0.685	Towards Accurate Multi-person Pose Estimation in the Wild
Supervising Self-Attention	0.665	Attend to Who You Are: Supervising Self-Attention for Keypoint Detection and Instance-Aware Association
Associative Embedding	0.655	Associative Embedding: End-to-End Learning for Joint Detection and Grouping
G-RMI	0.649	Towards Accurate Multi-person Pose Estimation in the Wild
PoseFix	-	PoseFix: Model-agnostic General Human Pose Refinement Network
LitePose-S	-	Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation
EvoPose2D-L	-	EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight Transfer

0 of 15 row(s) selected.