Pedestrian Attribute Recognition
28 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
Most implemented papers
Spatio-Temporal Side Tuning Pre-trained Foundation Models for Video-based Pedestrian Attribute Recognition
wangxiao5791509/Pedestrian-Attribute-Recognition-Paper-List
•
•
Specifically, we formulate the video-based PAR as a vision-language fusion problem and adopt a pre-trained foundation model CLIP to extract the visual features.
Pedestrian Attribute Recognition: A Survey
wangxiao5791509/Pedestrian-Attribute-Recognition-Paper-List
•
•
We also review some popular network architectures which have been widely applied in the deep learning community.
Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization
chufengt/iccv19_attribute
•
•
ICCV 2019
To predict the existence of a particular attribute, it is demanded to localize the regions related to the attribute.
Rethinking of Pedestrian Attribute Recognition: A Reliable Evaluation under Zero-Shot Pedestrian Identity Setting
valencebond/Rethinking_of_PAR
•
•
Second, based on the proposed definition, we expose the limitations of the existing datasets, which violate the academic norm and are inconsistent with the essential requirement of practical industry application.
Label2Label: A Language Modeling Framework for Multi-Attribute Learning
As each sample is annotated with multiple attribute labels, these "words" will naturally form an unordered but meaningful "sentence", which depicts the semantic information of the corresponding sample.
UPAR: Unified Pedestrian Attribute Recognition and Person Retrieval
It is based on four well-known person attribute recognition datasets: PA100K, PETA, RAPv2, and Market1501.
UniHCP: A Unified Model for Human-Centric Perceptions
opengvlab/unihcp
•
•
CVPR 2023
When adapted to a specific task, UniHCP achieves new SOTAs on a wide range of human-centric tasks, e. g., 69. 8 mIoU on CIHP for human parsing, 86. 18 mA on PA-100K for attribute prediction, 90. 3 mAP on Market1501 for ReID, and 85. 8 JI on CrowdHuman for pedestrian detection, performing better than specialized models tailored for each task.
HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining
opengvlab/humanbench
•
•
CVPR 2023
Specifically, we propose a \textbf{HumanBench} based on existing datasets to comprehensively evaluate on the common ground the generalization abilities of different pretraining methods on 19 datasets from 6 diverse downstream tasks, including person ReID, pose estimation, human parsing, pedestrian attribute recognition, pedestrian detection, and crowd counting.
POAR: Towards Open Vocabulary Pedestrian Attribute Recognition
IvyYZ/POAR
•
•
Our key idea is to formulate the POAR problem as an image-text search problem.
PARFormer: Transformer-based Multi-Task Network for Pedestrian Attribute Recognition
xwf199/parformer
•
•
Pedestrian attribute recognition (PAR) has received increasing attention because of its wide application in video surveillance and pedestrian analysis.
