Text-based Aerial-Ground Person Retrieval
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (34) · 29035-29043
DOI: 10.1609/aaai.v40i34.40140 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Xinyu Zhou und 5 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref).
Abstract (Originalsprache)
This work introduces Text-based Aerial-Ground Person Retrieval (TAG-PR), which aims to retrieve person images from heterogeneous aerial and ground views with textual descriptions. Unlike traditional Text-based Person Retrieval (T-PR), which focuses solely on ground-view images, TAG-PR introduces greater practical significance and presents unique challenges due to the large viewpoint discrepancy across images. To support this task, we contribute: (1) TAG-PEDES dataset, constructed from public benchmarks with automatically generated textual descriptions, enhanced by a diversified text generation paradigm to ensure robustness under view heterogeneity; and (2) TAG-CLIP, a novel retrieval framework that addresses view heterogeneity through a hierarchically-routed mixture of experts module to learn view-specific and view-agnostic features and a viewpoint decoupling strategy to decouple view-specific features for better cross-modal alignment. We evaluate the effectiveness of TAG-CLIP on both the proposed TAG-PEDES and existing T-PR benchmarks.
Zitieren
APA
Zhou, X., Wu, Y., Ma, J., Wang, W., Cao, M., & Ye, M. (2026). Text-based Aerial-Ground Person Retrieval. Proceedings of the AAAI Conference on Artificial Intelligence, 40(34), 29035-29043. https://doi.org/10.1609/aaai.v40i34.40140
Vancouver
Zhou X, Wu Y, Ma J, Wang W, Cao M, Ye M. Text-based Aerial-Ground Person Retrieval. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(34):29035-29043. doi:10.1609/aaai.v40i34.40140
BibTeX
@article{Zhou2026,
author = {Zhou, Xinyu and Wu, Yu and Ma, Jiayao and Wang, Wenhao and Cao, Min and Ye, Mang},
title = {Text-based Aerial-Ground Person Retrieval},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {34},
pages = {29035--29043},
doi = {10.1609/aaai.v40i34.40140}
}
EUVIMED