Datasets › PA-100K

PA-100K (PA-100K Dataset)

Introduced by Xihui Liu et al. in HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis1 Jan 2017 archive 2025-07-28

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

Benchmarks archive 2025-07-28

All 1 leaderboard whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Pedestrian Attribute Recognition PA-100K PATH (Partial FT) Accuracy 90.8 HumanBench: Towards General Human-centric Perception... opengvlab/humanbench 13 Compare

Papers archive 2025-07-28

11 shown of 11 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 56. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
AttriVision: Advancing Generalization in Pedestrian Attribute Recognition using CLIP 0 2 18 Feb 2025 not harvested
C2T-Net: Channel-Aware Cross-Fused Transformer-Style Networks for Pedestrian Attribute Recognition 1 1 26 Dec 2023 not harvested
Hulk: A Universal Knowledge Translator for Human-Centric Tasks 2 2 4 Dec 2023 ran 12 of 24 samples (12 unverified)
Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark 1 1 5 Jun 2023 ran 6 of 12 samples (6 unverified)
Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks 4 1 30 Mar 2023 ran 1 of 2 samples (1 unverified; 1 pointer-only for licence)
HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining 1 1 10 Mar 2023 ran 15 of 25 samples (10 unverified)
UniHCP: A Unified Model for Human-Centric Perceptions 1 1 6 Mar 2023 ran 7 of 13 samples (6 unverified)
Label2Label: A Language Modeling Framework for Multi-Attribute Learning 1 1 18 Jul 2022 ran 2 of 5 samples (3 unverified; 5 pointer-only for licence)
Rethinking of Pedestrian Attribute Recognition: Realistic Datasets with Efficient Method 2 1 25 May 2020 not harvested
Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization 2 1 10 Oct 2019 ran 1 of 3 samples (2 unverified)
HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis 2 1 28 Sep 2017 not harvested

Dataset loaders archive 2025-07-28

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • PA-100K

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections