PA-100K

PA-100K Dataset

Dataset Information
Modalities
Images
Languages
English, Chinese
Introduced
2017
License
Unknown
Homepage
Official Website
Contents

Overview

PA-100K is a recent-proposed large pedestrian attribute dataset, with 100,000 images in total collected from outdoor surveillance cameras. It is split into 80,000 images for the training set, and 10,000 for the validation set and 10,000 for the test set. This dataset is labeled by 26 binary attributes. The common features existing in both selected dataset is that the images are blurry due to the relatively low resolution and the positive ratio of each binary attribute is low.

Source: Localization Guided Learning for Pedestrian Attribute Recognition
Image Source: https://github.com/xh-liu/HydraPlus-Net

Variants: PA-100K

Associated Benchmarks

This dataset is used in 1 benchmark:

Recent Benchmark Submissions

Task Model Paper Date
Pedestrian Attribute Recognition Hulk(Finetune, ViT-L) Hulk: A Universal Knowledge Translator … 2023-12-04
Pedestrian Attribute Recognition Hulk(Finetune, ViT-B) Hulk: A Universal Knowledge Translator … 2023-12-04
Pedestrian Attribute Recognition APTM Towards Unified Text-based Person Retrieval: … 2023-06-05
Pedestrian Attribute Recognition SOLIDER Beyond Appearance: a Semantic Controllable … 2023-03-30
Pedestrian Attribute Recognition PATH (Partial FT) HumanBench: Towards General Human-centric Perception … 2023-03-10
Pedestrian Attribute Recognition UniHCP (finetune) UniHCP: A Unified Model for … 2023-03-06
Pedestrian Attribute Recognition Label2Label Label2Label: A Language Modeling Framework … 2022-07-18
Pedestrian Attribute Recognition strongBaseline(ours) Rethinking of Pedestrian Attribute Recognition: … 2020-05-25
Pedestrian Attribute Recognition Attribute-Specific Localization Improving Pedestrian Attribute Recognition With … 2019-10-10
Pedestrian Attribute Recognition HP-net HydraPlus-Net: Attentive Deep Features for … 2017-09-28

Research Papers

Recent papers with results on this dataset:

External Links: