# Pedestrian Attribute Recognition via Hierarchical Cross-Modality HyperGraph Learning

arXiv: https://arxiv.org/abs/2509.22331 · HTML: https://mlsanity.com/paper/2509.22331/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 46 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Builds on (most cited first, 26 of 26)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Session-based Recommendation with Graph Neural Networks](https://mlsanity.com/paper/1811.00855/) (2018)
- [UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks](https://mlsanity.com/paper/2105.00956/) (2021)
- [Improving Person Re-identification by Attribute and Identity Learning](https://mlsanity.com/paper/1703.07220/) (2017)
- [HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis](https://mlsanity.com/paper/1709.09930/) (2017)
- [State Space Model for New-Generation Network Alternative to Transformers: A Survey](https://mlsanity.com/paper/2404.09516/) (2024)
- [Deep Imbalanced Attribute Classification using Visual Attention Aggregation](https://mlsanity.com/paper/1807.03903/) (2018)
- [Pedestrian Attribute Recognition: A Survey](https://mlsanity.com/paper/1901.07474/) (2019)
- [A Richly Annotated Dataset for Pedestrian Attribute Recognition](https://mlsanity.com/paper/1603.07054/) (2016)
- [HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception](https://mlsanity.com/paper/2310.20695/) (2023)
- [Spatial and Semantic Consistency Regularizations for Pedestrian Attribute Recognition](https://mlsanity.com/paper/2109.05686/) (2021)
- [Rethinking of Pedestrian Attribute Recognition: A Reliable Evaluation under Zero-Shot Pedestrian Identity Setting](https://mlsanity.com/paper/2107.03576/) (2021)
- [Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion](https://mlsanity.com/paper/2312.10692/) (2023)
- [Label2Label: A Language Modeling Framework for Multi-Attribute Learning](https://mlsanity.com/paper/2207.08677/) (2022)
- [Multi-task CNN Model for Attribute Prediction](https://mlsanity.com/paper/1601.00400/) (2016)
- [Attribute-aware Pedestrian Detection in a Crowd](https://mlsanity.com/paper/1910.09188/) (2019)
- [PARFormer: Transformer-based Multi-Task Network for Pedestrian Attribute Recognition](https://mlsanity.com/paper/2304.07230/) (2023)
- [SequencePAR: Understanding Pedestrian Attributes via A Sequence Generation Paradigm](https://mlsanity.com/paper/2312.01640/) (2023)
- [A Solution to Co-occurrence Bias: Attributes Disentanglement via Mutual Information Minimization for Pedestrian Attribute Recognition](https://mlsanity.com/paper/2307.15252/) (2023)
- [An Empirical Study of Mamba-based Pedestrian Attribute Recognition](https://mlsanity.com/paper/2407.10374/) (2024)
- [Pedestrian Attribute Recognition: A New Benchmark Dataset and A Large Language Model Augmented Framework](https://mlsanity.com/paper/2408.09720/) (2024)
- [Pedestrian Attribute Recognition as Label-balanced Multi-label Learning](https://mlsanity.com/paper/2405.04858/) (2024)
- [SSPNet: Scale and Spatial Priors Guided Generalizable and Interpretable Pedestrian Attribute Recognition](https://mlsanity.com/paper/2312.06049/) (2023)
- [AttMOT: Improving Multiple-Object Tracking by Introducing Auxiliary Pedestrian Attributes](https://mlsanity.com/paper/2308.07537/) (2023)
- [DeepCAMP: Deep Convolutional Action & Attribute Mid-Level Patterns](https://mlsanity.com/paper/1608.03217/) (2016)
- [FOCUS: Fine-grained Optimization with Semantic Guided Understanding for Pedestrian Attributes Recognition](https://mlsanity.com/paper/2506.22836/) (2025)

## Built on by (most cited first, 2 of 2)

- [Uncertainty-Aware Pedestrian Attribute Recognition via Evidential Deep Learning](https://mlsanity.com/paper/2604.26873/) (2026)
- [EPRBench: A High-Quality Benchmark Dataset for Event Stream Based Visual Place Recognition](https://mlsanity.com/paper/2602.12919/) (2026)

## Abstract (arXiv)

Current Pedestrian Attribute Recognition (PAR) algorithms typically focus on mapping visual features to semantic labels or attempt to enhance learning by fusing visual and attribute information. However, these methods fail to fully exploit attribute knowledge and contextual information for more accurate recognition. Although recent works have started to consider using attribute text as additional input to enhance the association between visual and semantic information, these methods are still in their infancy. To address the above challenges, this paper proposes the construction of a multi-modal knowledge graph, which is utilized to mine the relationships between local visual features and text, as well as the relationships between attributes and extensive visual context samples. Specifically, we propose an effective multi-modal knowledge graph construction method that fully considers the relationships among attributes and the relationships between attributes and vision tokens. To effectively model these relationships, this paper introduces a knowledge graph-guided cross-modal hypergraph learning framework to enhance the standard pedestrian attribute recognition framework. Comprehensive experiments on multiple PAR benchmark datasets have thoroughly demonstrated the effectiveness of our proposed knowledge graph for the PAR task, establishing a strong foundation for knowledge-guided pedestrian attribute recognition. The source code of this paper will be released on https://github.com/Event-AHU/OpenPAR