HiHR: Hierarchical Hyperbolic Representation for Aerial-Ground Person Re-Identification
2026-07-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors focus on recognizing the same person from cameras on drones and on the ground, which is tricky due to differences in viewpoints. They created a new method called HiHR that first extracts detailed features using visual and text data, then combines these features guided by text for better identity representation. Their approach uses a special learning system that organizes these features in layers within a hyperbolic space, helping separate identities while keeping unique camera-view details. Tests on multiple datasets show their method works well for this problem.
Person Re-IdentificationAerial-Ground CamerasFeature ExtractionVisual-Text EncodersMulti-Granularity FeaturesHyperbolic SpaceHierarchical LearningCross-View Consistency
Authors
Qiwei Yang, Pingping Zhang
Abstract
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.