Pedestrian Attribute Recognition
27 papers with code • 5 benchmarks • 5 datasets
Pedestrian attribution recognition is the task of recognizing pedestrian features - such as whether they are talking on a phone, whether they have a backpack, and so on.
( Image credit: HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis )
Benchmarks
These leaderboards are used to track progress in Pedestrian Attribute Recognition
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Pedestrian Attribute Recognition models and implementations
PETA
PA-100K
UAV-Human
RAP
CAR
Latest papers
C2T-Net: Channel-Aware Cross-Fused Transformer-Style Networks for Pedestrian Attribute Recognition
caodoanh2001/upar_challenge
•
•
WACV202 2023
Our performance on the PETA dataset remains competitive, standing on par with other cutting-edge models.
Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion
wangxiao5791509/Pedestrian-Attribute-Recognition-Paper-List
•
•
In this paper, we formulate PAR as a vision-language fusion problem and fully exploit the relations between pedestrian images and attribute labels.
SSPNet: Scale and Spatial Priors Guided Generalizable and Interpretable Pedestrian Attribute Recognition
guotengg/sspnet
•
•
The AFSS module learns to provide reasonable scale prior information for different attribute groups, allowing the model to focus on different levels of feature maps with varying semantic granularity.
SequencePAR: Understanding Pedestrian Attributes via A Sequence Generation Paradigm
wangxiao5791509/Pedestrian-Attribute-Recognition-Paper-List
•
•
Then, a Transformer decoder is proposed to generate the human attributes by incorporating the visual features and attribute query tokens.
Hulk: A Universal Knowledge Translator for Human-Centric Tasks
Human-centric perception tasks, e. g., pedestrian detection, skeleton-based action recognition, and pose estimation, have wide industrial applications, such as metaverse and sports analysis.
HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception
junkunyuan/hap
•
•
NeurIPS 2023
To further capture human characteristics, we propose a structure-invariant alignment loss that enforces different masked views, guided by the human part prior, to be closely aligned for the same image.
A Solution to Co-occurrence Bias: Attributes Disentanglement via Mutual Information Minimization for Pedestrian Attribute Recognition
sdret/a-solution-to-co-occurence-bias-in-pedestrian-attribute-recognition
•
•
Recent studies on pedestrian attribute recognition progress with either explicit or implicit modeling of the co-occurrence among attributes.
Lightweight Attribute Localizing Models for Pedestrian Attribute Recognition
ashishjv1/LW-ALM
•
•
Pedestrian Attribute Recognition (PAR) deals with the problem of identifying features in a pedestrian image.
Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark
Shuyu-XJTU/APTM
•
•
To verify the feasibility of learning from the generated data, we develop a new joint Attribute Prompt Learning and Text Matching Learning (APTM) framework, considering the shared knowledge between attribute and text.
PLIP: Language-Image Pre-training for Person Representation Learning
zplusdragon/plip
•
•
Extensive experiments demonstrate that our model not only significantly improves existing methods on all these tasks, but also shows great ability in the few-shot and domain generalization settings.
