EUVIMEDEUVIMED entdecken
Crossref

Pedestrian Attribute Recognition: A New Benchmark Dataset and a Large Language Model Augmented Framework

Jiandong Jin, Xiao Wang, Qian Zhu, Haiyang Wang, Chenglong Li

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (4) · 4138-4146

DOI: 10.1609/aaai.v39i4.32434 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Jiandong Jin und 4 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Pedestrian Attribute Recognition (PAR) is one of the indispensable tasks in human-centered research. However, existing datasets neglect different domains (e.g., environments, times, populations, and data sources), only conducting simple random splits, and the performance of these datasets has already approached saturation. In the past five years, no large-scale dataset has been opened to the public. To address this issue, this paper proposes a new large-scale, cross-domain pedestrian attribute recognition dataset to fill the data gap, termed MSP60K. It consists of 60,122 images and 57 attribute annotations across eight scenarios. Synthetic degradation is also conducted to further narrow the gap between the dataset and real-world challenging scenarios. To establish a more rigorous benchmark, we evaluate 17 representative PAR models under both random and cross-domain split protocols on our dataset. Additionally, we propose an innovative Large Language Model (LLM) augmented PAR framework, named LLM-PAR. This framework processes pedestrian images through a Vision Transformer (ViT) backbone to extract features and introduces a multi-embedding query Transformer to learn partial-aware features for attribute classification. Significantly, we enhance this framework with LLM for ensemble learning and visual feature augmentation. Comprehensive experiments across multiple PAR benchmark datasets have thoroughly validated the efficacy of our proposed framework.

Zitieren

APA

Jin, J., Wang, X., Zhu, Q., Wang, H., & Li, C. (2025). Pedestrian Attribute Recognition: A New Benchmark Dataset and a Large Language Model Augmented Framework. Proceedings of the AAAI Conference on Artificial Intelligence, 39(4), 4138-4146. https://doi.org/10.1609/aaai.v39i4.32434

Vancouver

Jin J, Wang X, Zhu Q, Wang H, Li C. Pedestrian Attribute Recognition: A New Benchmark Dataset and a Large Language Model Augmented Framework. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(4):4138-4146. doi:10.1609/aaai.v39i4.32434

BibTeX
@article{Jin2025,
  author = {Jin, Jiandong and Wang, Xiao and Zhu, Qian and Wang, Haiyang and Li, Chenglong},
  title = {Pedestrian Attribute Recognition: A New Benchmark Dataset and a Large Language Model Augmented Framework},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {4},
  pages = {4138--4146},
  doi = {10.1609/aaai.v39i4.32434}
}
Kostenlos starten →