# FOCUS: Fine-grained Optimization with Semantic Guided Understanding for Pedestrian Attributes Recognition

arXiv: https://arxiv.org/abs/2506.22836 · HTML: https://mlsanity.com/paper/2506.22836/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 22 references that are in the map.
- First posted on arXiv 28 Jun 2025.

## Builds on (most cited first, 9 of 9)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis](https://mlsanity.com/paper/1709.09930/) (2017)
- [A Richly Annotated Dataset for Pedestrian Attribute Recognition](https://mlsanity.com/paper/1603.07054/) (2016)
- [Spatial and Semantic Consistency Regularizations for Pedestrian Attribute Recognition](https://mlsanity.com/paper/2109.05686/) (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)
- [Localization Guided Learning for Pedestrian Attribute Recognition](https://mlsanity.com/paper/1808.09102/) (2018)
- [POAR: Towards Open Vocabulary Pedestrian Attribute Recognition](https://mlsanity.com/paper/2303.14643/) (2023)

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

- [Pedestrian Attribute Recognition via Hierarchical Cross-Modality HyperGraph Learning](https://mlsanity.com/paper/2509.22331/) (2025)
- [Uncertainty-Aware Pedestrian Attribute Recognition via Evidential Deep Learning](https://mlsanity.com/paper/2604.26873/) (2026)

## Abstract (arXiv)

Pedestrian attribute recognition (PAR) is a fundamental perception task in intelligent transportation and security. To tackle this fine-grained task, most existing methods focus on extracting regional features to enrich attribute information. However, a regional feature is typically used to predict a fixed set of pre-defined attributes in these methods, which limits the performance and practicality in two aspects: 1) Regional features may compromise fine-grained patterns unique to certain attributes in favor of capturing common characteristics shared across attributes. 2) Regional features cannot generalize to predict unseen attributes in the test time. In this paper, we propose the Fine-grained Optimization with semantiC gUided underStanding (FOCUS) approach for PAR, which adaptively extracts fine-grained attribute-level features for each attribute individually, regardless of whether the attributes are seen or not during training. Specifically, we propose the Multi-Granularity Mix Tokens (MGMT) to capture latent features at varying levels of visual granularity, thereby enriching the diversity of the extracted information. Next, we introduce the Attribute-guided Visual Feature Extraction (AVFE) module, which leverages textual attributes as queries to retrieve their corresponding visual attribute features from the Mix Tokens using a cross-attention mechanism. To ensure that textual attributes focus on the appropriate Mix Tokens, we further incorporate a Region-Aware Contrastive Learning (RACL) method, encouraging attributes within the same region to share consistent attention maps. Extensive experiments on PA100K, PETA, and RAPv1 datasets demonstrate the effectiveness and strong generalization ability of our method.