HyperAI
الرئيسية
الأخبار
أحدث الأوراق البحثية
الدروس
مجموعات البيانات
الموسوعة
SOTA
نماذج LLM
لوحة الأداء GPU
الفعاليات
البحث
حول
العربية
HyperAI
Toggle sidebar
البحث في الموقع...
⌘
K
الرئيسية
SOTA
Pose Estimation
Pose Estimation On Crowdpose
Pose Estimation On Crowdpose
المقاييس
AP
AP50
AP75
APM
Test
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
Columns
اسم النموذج
AP
AP50
AP75
APM
Test
Paper Title
Repository
KAPAO-S
63.8
87.7
69.4
64.8
72.1
Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation
BUCTD-W48
72.9
-
-
-
-
Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity
KAPAO-M
67.1
88.8
73.4
68.1
75.2
Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation
OpenPifPaf
70.5
89.1
76.1
-
-
OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association
SwinV2-L 1K-MIM
75.5
-
-
-
-
Revealing the Dark Secrets of Masked Image Modeling
MIPNet (HRNet-W48)
70.0
-
-
71.1
-
Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation
KAPAO-L
68.9
89.4
75.6
69.9
76.6
Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation
BUCTD-W48 (w/cond. input from PETR)
76.7
-
-
-
-
Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity
SwinV2-B 1K-MIM
74.9
-
-
-
-
Revealing the Dark Secrets of Masked Image Modeling
BUCTD-W48 (w/cond. input from PETR, and generative sampling)
78.5
-
-
-
-
Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity
Hourglass-104
65.2
85.9
69.5
66.2
-
Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation
ViTPose-G
78.3
85.3
81.4
86.6
-
ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation
0 of 12 row(s) selected.
Previous
Next