Towards Generalized Pedestrian Attribute Recognition Via Hierarchical Prompts and Visual-Semantic Interaction
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026 · 1-17
DOI: 10.1109/tpami.2026.3748100 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026. Verfasst von Junyi Wu und 5 weiteren Autor:innen.
Abstract (Originalsprache)
Pedestrian attribute recognition (PAR) aims to predict multiple semantic attributes of a person from images. Existing unimodal methods focus on learning robust visual features but fail to exploit linguistic semantics, while recent bimodal approaches rely on static prompt templates and shallow fusion, limiting their ability to model intra-class attribute variability and modality collaboration. To address these limitations, we propose a generalized PAR framework based on Hierarchical Prompt Learning and Visual-Semantic Interaction (HPLVSI). Specifically, we introduce an Image-Conditional Hierarchical-Prompt Initialization Module (IHIM) to generate context-sensitive prompts from visual inputs, and a Hierarchical Prompt Optimization (HPO) strategy to mitigate prompt overfitting and enhance attribute discrimination. To further strengthen cross-modal reasoning, a Prompt Enhancement and Regularization Module (PERM) refines linguistic representations, while a Bimodal Mutual Interaction Module (BMIM) enables effective bidirectional visual-textual collaboration. In addition, to better reflect real-world distribution shifts, we construct a new large-scale dataset, Celeb-PAR, based on long-term person re-identification data, and establish a new cross-domain PAR benchmark. Extensive experiments demonstrate that our method consistently outperforms state-of-the-art approaches (e.g., 88.97% mA on PA100K) under both standard and cross-domain settings, validating its strong generalization capability and real-world applicability.
Zitieren
APA
Wu, J., Huang, Y., Gao, M., Niu, Y., Chen, Y., & Wu, Q. (2026). Towards Generalized Pedestrian Attribute Recognition Via Hierarchical Prompts and Visual-Semantic Interaction. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1-17. https://doi.org/10.1109/tpami.2026.3748100
Vancouver
Wu J, Huang Y, Gao M, Niu Y, Chen Y, Wu Q. Towards Generalized Pedestrian Attribute Recognition Via Hierarchical Prompts and Visual-Semantic Interaction. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026:1-17. doi:10.1109/tpami.2026.3748100
BibTeX
@article{Wu2026,
author = {Wu, Junyi and Huang, Yan and Gao, Min and Niu, Yuzhen and Chen, Yuzhong and Wu, Qiang},
title = {Towards Generalized Pedestrian Attribute Recognition Via Hierarchical Prompts and Visual-Semantic Interaction},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
pages = {1--17},
doi = {10.1109/tpami.2026.3748100}
}
EUVIMED