mlsanityData to 14 Oct 2026

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

arXiv 2512.22217 ↗First posted 22 Dec 2025cs.CV cs.AIcited by 0

On the map: Multimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection

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.

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.

Builds on

8 of 15 references.

References · 8

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  3. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,188
  4. 2017Improving Person Re-identification by Attribute and Identity Learningcited by 96
  5. 2017HydraPlus-Net: Attentive Deep Features for Pedestrian Analysiscited by 89
  6. 2021Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translationcited by 74
  7. 2023SSPNet: Scale and Spatial Priors Guided Generalizable and Interpretable Pedestrian Attribute Recognitioncited by 7
  8. 2024CLEAR: Cross-Transformers with Pre-trained Language Model is All you need for Person Attribute Recognition and Retrievalcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion
  2. 2025A Data-Centric Approach to Pedestrian Attribute Recognition: Synthetic Augmentation via Prompt-driven Diffusion Models
  3. 2026ReSAGE-PAR: Representational Similarity Assessment for Generative Expansion in Pedestrian Attribute Recognition
  4. 2024When Large Vision-Language Models Meet Person Re-Identification
  5. 2024ArtVLM: Attribute Recognition Through Vision-Based Prefix Language Modeling
  6. 2024An Empirical Study of Mamba-based Pedestrian Attribute Recognition
  7. 2025Black Sheep in the Herd: Playing with Spuriously Correlated Attributes for Vision-Language Recognition
  8. 2023Vision-Language Models for Vision Tasks: A Survey