HyperAI
Home
News
Latest Papers
Tutorials
Datasets
Wiki
SOTA
LLM Models
GPU Leaderboard
Events
Search
About
English
System
HyperAI
Toggle sidebar
Search the site…
⌘
K
Login
Login
Home
SOTA
Pedestrian Attribute Recognition
Pedestrian Attribute Recognition On Pa 100K
Pedestrian Attribute Recognition On Pa 100K
Metrics
Accuracy
Results
Performance results of various models on this benchmark
Columns
Model Name
Accuracy
Paper Title
Repository
strongBaseline(ours)
78.56
Rethinking of Pedestrian Attribute Recognition: Realistic Datasets with Efficient Method
PATH (Partial FT)
90.8
HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining
HP-net
72.19%
HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis
UniHCP (finetune)
86.18
UniHCP: A Unified Model for Human-Centric Perceptions
Label2Label
79.23
Label2Label: A Language Modeling Framework for Multi-Attribute Learning
APTM
80.17
Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark
Hulk(Finetune, ViT-B)
87.85
Hulk: A Universal Knowledge Translator for Human-Centric Tasks
Hulk(Finetune, ViT-L)
88.97
Hulk: A Universal Knowledge Translator for Human-Centric Tasks
Attribute-Specific Localization
77.08%
Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization
C2T-Net
87.2
C2T-Net: Channel-Aware Cross-Fused Transformer-Style Networks for Pedestrian Attribute Recognition
SOLIDER
86.38
Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks
0 of 11 row(s) selected.
Previous
Next