HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Multi Person Pose Estimation On Coco Test Dev

평가 지표

AP

APL

APM

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	AP	APL	APM	Paper Title	Repository
Hourglass-104	65.6	68.8	63.3	Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation
SPM	66.9	73.1	62.6	Single-Stage Multi-Person Pose Machines
HigherHRNet (ScaleNet_P4)	71.6	77.2	67.5	ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual Recognition	-
Identity Mapping Hourglass	68.1	70.5	66.8	Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation
ResNet50	73.7	-	-	AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping Augmentation
CMU-Pose	61.8	68.2	57.1	Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
HRNet-W32	76.2	-	-	AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping Augmentation
PersonLab	68.7	75.5	64.1	PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model
HigherHRNet (HR-Net-48)	70.5	75.8	66.6	HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
G-RMI	64.9	70.0	62.3	Towards Accurate Multi-person Pose Estimation in the Wild	-
RMPE	61.8	67.6	58.6	RMPE: Regional Multi-person Pose Estimation
SMPR (HR-Net-32)	70.2	77.2	65.9	SMPR: Single-Stage Multi-Person Pose Regression
SCIO (HRNet-48)	79.2	84.2	74.1	Self-Constrained Inference Optimization on Structural Groups for Human Pose Estimation	-
HRNet-W48plus	78.7	-	-	AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping Augmentation
Supervising Self-Attention	66.5	-	-	Attend to Who You Are: Supervising Self-Attention for Keypoint Detection and Instance-Aware Association

0 of 15 row(s) selected.