Text-based Aerial-Ground Person Retrieval
Xinyu Zhou, Yu Wu, Jiayao Ma, Wenhao Wang, Min Cao, Mang Ye
Abstract
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 dataset and existing T-PR benchmarks. The dataset and code are available at https://github.com/Flame-Chasers/TAG-PR .
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Learning Granularity-Unified Representations for Text-to-Image Person Re-identification cites DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval
- Learning Granularity-Unified Representations for Text-to-Image Person Re-identification cites Pose-Guided Multi-Granularity Attention Network for Text-Based Person Search
- DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval cites Pose-Guided Multi-Granularity Attention Network for Text-Based Person Search
Builds on20
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- DSSL: Deep Surroundings-person Separation Learning for Text-based Person RetrievalAichun Zhu, Zijie Wang, Yifeng Li, Xili Wan et al.ACM MM 2021 · 274 citations
- Learning Granularity-Unified Representations for Text-to-Image Person Re-identificationZhiyin Shao, Xinyu Zhang, Meng Fang, Zhifeng Lin et al.ACM MM 2022 · 197 citations
- Pose-Guided Multi-Granularity Attention Network for Text-Based Person SearchYa Jing, Chenyang Si, Junbo Wang, Wei Wang et al.AAAI 2020 · 182 citations
- NFormer: Robust Person Re-identification with Neighbor TransformerHaochen Wang, Jiayi Shen, Yongtuo Liu, Yan Gao et al.CVPR 2022 · 172 citations
Related papers
- Cross-modal Fuzzy Alignment Network for Text-Aerial Person Retrieval and A Large-scale BenchmarkYifei Deng, Chenglong Li, Yuyang Zhang, Guyue Hu et al.CVPR 2026
- Semantic-Driven Visual Progressive Refinement for Aerial-Ground Person ReID: A Challenging Large-Scale BenchmarkAihua Zheng, Hao Xie, Xixi Wan, Zi Wang et al.AAAI 2026
- View-decoupled Transformer for Person Re-identification under Aerial-ground Camera NetworkQuan Zhang, Lei Wang, Vishal M. Patel, Xiaohua Xie et al.CVPR 2024 · 30 citations
- Ground-to-Aerial Person Search: Benchmark Dataset and ApproachShizhou Zhang, Qingchun Yang, De Cheng, Yinghui Xing et al.ACM MM 2023 · 17 citations
- AG-VPReID: A Challenging Large-Scale Benchmark for Aerial-Ground Video-based Person Re-IdentificationHuy Nguyen, Kien Nguyen, Akila Pemasiri, Feng Liu et al.CVPR 2025
