# VLM-PAR: A Vision Language Model for Pedestrian Attribute Recognition

arXiv: https://arxiv.org/abs/2512.22217 · HTML: https://mlsanity.com/paper/2512.22217/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Driving VLMs and open-vocabulary detection, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 8 of its 15 references that are in the map.
- First posted on arXiv 22 Dec 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Driving VLMs and open-vocabulary detection](https://mlsanity.com/mllm/driving-vlms-and-open-vocabulary-detection/)

## Builds on (most cited first, 8 of 8)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [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)
- [Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation](https://mlsanity.com/paper/2104.08771/) (2021)
- [SSPNet: Scale and Spatial Priors Guided Generalizable and Interpretable Pedestrian Attribute Recognition](https://mlsanity.com/paper/2312.06049/) (2023)
- [CLEAR: Cross-Transformers with Pre-trained Language Model is All you need for Person Attribute Recognition and Retrieval](https://mlsanity.com/paper/2403.06119/) (2024)

## Abstract (arXiv)

Pedestrian Attribute Recognition (PAR) involves predicting fine-grained attributes such as clothing color, gender, and accessories from pedestrian imagery, yet is hindered by severe class imbalance, intricate attribute co-dependencies, and domain shifts. We introduce VLM-PAR, a modular vision-language framework built on frozen SigLIP 2 multilingual encoders. By first aligning image and prompt embeddings via refining visual features through a compact cross-attention fusion, VLM-PAR achieves significant accuracy improvement on the highly imbalanced PA100K benchmark, setting a new state-of-the-art performance, while also delivering significant gains in mean accuracy across PETA and Market-1501 benchmarks. These results underscore the efficacy of integrating large-scale vision-language pretraining with targeted cross-modal refinement to overcome imbalance and generalization challenges in PAR.