EUVIMEDEUVIMED entdecken
Crossref

Diverse Person: Customize Your Own Dataset for Text-Based Person Search

Zifan Song, Guosheng Hu, Cairong Zhao

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (5) · 4943-4951

DOI: 10.1609/aaai.v38i5.28298 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Zifan Song und 2 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Text-based person search is a challenging task aimed at locating specific target pedestrians through text descriptions. Recent advancements have been made in this field, but there remains a deficiency in datasets tailored for text-based person search. The creation of new, real-world datasets is hindered by concerns such as the risk of pedestrian privacy leakage and the substantial costs of annotation. In this paper, we introduce a framework, named Diverse Person (DP), to achieve efficient and high-quality text-based person search data generation without involving privacy concerns. Specifically, we propose to leverage available images of clothing and accessories as reference attribute images to edit the original dataset images through diffusion models. Additionally, we employ a Large Language Model (LLM) to produce annotations that are both high in quality and stylistically consistent with those found in real-world datasets. Extensive experimental results demonstrate that the baseline models trained with our DP can achieve new state-of-the-art results on three public datasets, with performance improvements up to 4.82%, 2.15%, and 2.28% on CUHK-PEDES, ICFG-PEDES, and RSTPReid in terms of Rank-1 accuracy, respectively.

Zitieren

APA

Song, Z., Hu, G., & Zhao, C. (2024). Diverse Person: Customize Your Own Dataset for Text-Based Person Search. Proceedings of the AAAI Conference on Artificial Intelligence, 38(5), 4943-4951. https://doi.org/10.1609/aaai.v38i5.28298

Vancouver

Song Z, Hu G, Zhao C. Diverse Person: Customize Your Own Dataset for Text-Based Person Search. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(5):4943-4951. doi:10.1609/aaai.v38i5.28298

BibTeX
@article{Song2024,
  author = {Song, Zifan and Hu, Guosheng and Zhao, Cairong},
  title = {Diverse Person: Customize Your Own Dataset for Text-Based Person Search},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {5},
  pages = {4943--4951},
  doi = {10.1609/aaai.v38i5.28298}
}
Kostenlos starten →