HyperAI초신경
홈뉴스최신 연구 논문튜토리얼데이터셋백과사전SOTALLM 모델GPU 랭킹컨퍼런스
전체 검색
소개
HyperAI초신경

Pose Estimation On Ochuman

평가 지표

Test AP
Validation AP

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
Test AP
Validation AP
Paper TitleRepository
Associative Embedding29.532.1Associative Embedding: End-to-End Learning for Joint Detection and Grouping
BUCTD (CID-W32)47.247.7Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity
ViTPose (ViTAE-G, GT bounding boxes)93.392.8ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation
RTMPose(RTMPose-l, GT bounding boxes)80.380.5RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose
HQNet (ResNet-50)40.0-You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception
HQNet (ViT-L)45.6-You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception
HGG (AE+)36.041.8Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimation-
CID (HRNet-W48)45.046.1Contextual Instance Decoupling for Robust Multi-Person Pose Estimation
ResNet-15233.341.0Simple Baselines for Human Pose Estimation and Tracking
ResNet-5029.532.1Simple Baselines for Human Pose Estimation and Tracking
BBox-Mask-Pose 2x48.348.6Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle
TransPose-H-62.3TransPose: Keypoint Localization via Transformer
Associative Embedding+32.840.0Associative Embedding: End-to-End Learning for Joint Detection and Grouping
MIPNet (HRNet-W48)42.542.0Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation
RMPE30.738.8RMPE: Regional Multi-person Pose Estimation
MaskPose-b45.045.3Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle
UniHCP (direct eval)87.4-UniHCP: A Unified Model for Human-Centric Perceptions
HRNet-W4837.237.8Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation
0 of 18 row(s) selected.