发表机构
Dalian University of Technology（大连理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对空地行人重识别中跨视图特征对齐问题，提出HiHR框架，通过提取多粒度特征、文本引导多粒度融合及分层双曲学习，在双曲空间构建分层特征结构，有效聚合判别特征，经实验验证了该框架的有效性。
AI 中文摘要
空地行人重识别（AG-ReID）旨在跨异构的空中和地面相机平台检索同一个人。尽管已取得很大进展，但由于跨视图直接特征对齐，现有方法仍不理想，忽略了视图特定线索。为解决此问题，我们提出用于AG-ReID的新颖分层双曲表示（HiHR）框架。具体而言，首先基于预训练视觉文本编码器提取多粒度特征，接着提出文本引导多粒度融合（TMF）融合多粒度特征并增强身份特征表示能力。此外，引入分层双曲学习（HHL）在双曲空间构建分层特征结构。该分层包括确保身份可分离性和跨视图一致性的粗粒度级别以及保留视图特定判别线索的细粒度级别。实验表明该框架能有效聚合AG-ReID的视图不变和视图特定判别特征。
英文摘要
Aerial-Ground Person Re-IDentification (AG-ReID) aims to retrieve the same person across heterogeneous aerial and ground camera platforms. Although great progress has been made, existing methods remain suboptimal due to the direct feature alignment across views, overlooking view-specific cues. To address this issue, we propose a novel Hierarchical Hyperbolic Representation (HiHR) framework for AG-ReID. More specifically, we first extract multi-granularity features based on pre-trained visual-text encoders. Then, we propose a Text-guided Multi-granularity Fusion (TMF) to fuse multi-granularity features and enhance the representation ability of identity features. Furthermore, we introduce the Hierarchical Hyperbolic Learning (HHL) to construct a hierarchical feature structure in a hyperbolic space. This hierarchy includes a coarse level that ensures identity separability and cross-view consistency, and a fine level that preserves view-specific discriminative cues. As a result, our proposed framework can effectively aggregate view-invariant and view-specific discriminative features for AG-ReID. Extensive experiments on four AG-ReID benchmarks demonstrate the effectiveness of our framework. The source code is available at https://github.com/YangQiWei3/HiHR.
CommentsAccepted by ECCV2026. More modifications may be performed
