HyperAI
Accueil
Actualités
Articles de recherche récents
Tutoriels
Ensembles de données
Wiki
SOTA
Modèles LLM
Classement GPU
Événements
Recherche
À propos
Français
HyperAI
Toggle sidebar
Rechercher sur le site...
⌘
K
Accueil
SOTA
Multi Person Pose Estimation
Multi Person Pose Estimation On Crowdpose
Multi Person Pose Estimation On Crowdpose
Métriques
AP Easy
AP Hard
AP Medium
mAP @0.5:0.95
Résultats
Résultats de performance de divers modèles sur ce benchmark
Columns
Nom du modèle
AP Easy
AP Hard
AP Medium
mAP @0.5:0.95
Paper Title
Repository
Mask R-CNN
69.4
45.8
57.9
57.2
Mask R-CNN
TransPose-H
79.5
62.2
72.9
71.8
TransPose: Keypoint Localization via Transformer
AlphaPose
71.2
51.1
61.4
61.0
RMPE: Regional Multi-person Pose Estimation
RTMO-l
88.8
77.2
84.7
83.8
RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation
SCIO (HRNet-48)
-
-
72.2
71.5
Self-Constrained Inference Optimization on Structural Groups for Human Pose Estimation
-
OpenPose
62.7
32.3
58.7
-
OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
ROMP+CAR
-
-
-
58.6
Monocular, One-stage, Regression of Multiple 3D People
Hourglass-104
73.8
54.8
66.2
65.2
Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation
HigherHRNet(HR-Net-48)
75.8
58.9
68.1
67.6
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
BUCTD-W48 (w/cond. input from PETR, and generative sampling)
83.9
72.3
79.0
78.5
Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity
HigherHRNet (ScaleNet_P4)
-
-
-
71.3
ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual Recognition
-
LitePose-S
-
-
-
58.3
Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation
ROMP
-
-
-
55.6
Monocular, One-stage, Regression of Multiple 3D People
BAPose (W32)
79.9
61.3
73.4
72.2
BAPose: Bottom-Up Pose Estimation with Disentangled Waterfall Representations
MIPNet (HRNet-W48)
78.1
59.4
71.1
70.0
Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation
CenterGroup
76.6
61.5
70.0
69.4
The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimation
Joint-candidate SPPE +
75.5
57.4
66.3
66.0
CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark
I²R-Net (1st stage: HRFormer-B)
83.8
69.3
78.1
77.4
I^2R-Net: Intra- and Inter-Human Relation Network for Multi-Person Pose Estimation
HRFormer-B
80.0
62.4
73.5
72.4
HRFormer: High-Resolution Transformer for Dense Prediction
SPM
70.3
55.7
64.5
63.7
Single-Stage Multi-Person Pose Machines
0 of 23 row(s) selected.
Previous
Next