Pedestrian Attribute Recognition (PAR) plays a crucial role in various vision tasks such as person retrieval and identification. Most existing attribute-based retrieval methods operate under the closed-set assumption that all attribute classes are consistently available during both training and inference. However, this assumption limits their applicability in real-world scenarios where novel attributes may emerge. Moreover, predefined attributes in benchmark datasets are often generic and shared across individuals, making them less discriminative for retrieving the target person. To address these challenges, we propose the Open-Attribute Recognition for Person Retrieval (OAPR) task, which aims to retrieve individuals based on attribute cues, regardless of whether those attributes were seen during training. To support this task, we introduce a novel framework designed to learn generalizable body part representations that cover a broad range of attribute categories. Furthermore, we reconstruct four widely used datasets for open-attribute recognition. Comprehensive experiments on these datasets demonstrate the necessity of the OAPR task and the effectiveness of our framework. The source code and pre-trained models will be publicly available upon publication.
@article{arxiv.2508.01389,
title = {Open-Attribute Recognition for Person Retrieval: Finding People Through Distinctive and Novel Attributes},
author = {Minjeong Park and Hongbeen Park and Sangwon Lee and Yoonha Jang and Jinkyu Kim},
journal= {arXiv preprint arXiv:2508.01389},
year = {2025}
}