HyperAI
HyperAI
الرئيسية
المنصة
الوثائق
الأخبار
الأوراق البحثية
الدروس
مجموعات البيانات
الموسوعة
SOTA
نماذج LLM
لوحة الأداء GPU
الفعاليات
البحث
حول
شروط الخدمة
سياسة الخصوصية
العربية
HyperAI
HyperAI
Toggle Sidebar
البحث في الموقع...
⌘
K
Command Palette
Search for a command to run...
المنصة
الرئيسية
SOTA
تقدير الوضعية
Pose Estimation On Mpii Human Pose
Pose Estimation On Mpii Human Pose
المقاييس
PCKh-0.5
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
Columns
اسم النموذج
PCKh-0.5
Paper Title
PCT (swin-l, test set)
94.3
Human Pose as Compositional Tokens
Soft-gated Skip Connections
94.1
Toward fast and accurate human pose estimation via soft-gated skip connections
Cascade Feature Aggregation
93.9
Cascade Feature Aggregation for Human Pose Estimation
PCT (swin-b, test set)
93.8
Human Pose as Compositional Tokens
TransPose
93.5
TransPose: Keypoint Localization via Transformer
UniHCP (FT)
93.2
UniHCP: A Unified Model for Human-Centric Perceptions
4xRSN-50
93.0
Learning Delicate Local Representations for Multi-Person Pose Estimation
UniPose
92.7
UniPose: Unified Human Pose Estimation in Single Images and Videos
MSPN
92.6
Rethinking on Multi-Stage Networks for Human Pose Estimation
Spatial Context
92.5
Human Pose Estimation with Spatial Contextual Information
HRNet-W32
92.3
Deep High-Resolution Representation Learning for Human Pose Estimation
DLCM
92.3
Deeply Learned Compositional Models for Human Pose Estimation
Multi-Scale Structure-Aware Network
92.1
Multi-Scale Structure-Aware Network for Human Pose Estimation
Pyramid Residual Modules (PRMs)
92.0
Learning Feature Pyramids for Human Pose Estimation
Chen et al. ICCV'17
91.9
Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation
Chou et al. arXiv'17
91.8
Self Adversarial Training for Human Pose Estimation
Multi-Context Attention
91.5
Multi-Context Attention for Human Pose Estimation
Residual Hourglass +ASR+AHO
91.5
Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation
DU-Net
91.2
Quantized Densely Connected U-Nets for Efficient Landmark Localization
Stacked hourglass + Inception-resnet
91.2
Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation
0 of 46 row(s) selected.
Previous
Next