View-Aware Semantic Alignment for Aerial-Ground Person Re-Identification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Quan, Cai, Zeqiang, Zhao, Peiming, Wu, Jingze, Wu, Cailun, Chen, Hongbo, Lai, Jianhuang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914577687511040
author Zhang, Quan
Cai, Zeqiang
Zhao, Peiming
Wu, Jingze
Wu, Cailun
Chen, Hongbo
Lai, Jianhuang
author_facet Zhang, Quan
Cai, Zeqiang
Zhao, Peiming
Wu, Jingze
Wu, Cailun
Chen, Hongbo
Lai, Jianhuang
contents Aerial-Ground Person Re-Identification (AGPReID) remains highly challenging due to drastic viewpoint variations between drones and fixed cameras. Existing methods typically follow a view-invariant paradigm, aligning shared features across views to achieve robustness. However, view-invariant inherently enforces part-level alignment, which ignores view-specific cues and discriminative identity information. To this end, this work proposes ViSA (View-aware Semantic Alignment), a view-aware framework that achieves cross-view semantic consistency containing an Expert-driven Token Generation Module (ETGM) and a Dual-branch Local Fusion Module (DLFM). Technically, the former constructs a set of view-aware experts to generate adaptive semantic queries that perceive viewpoint-specific patterns, while the latter leverages graph reasoning to extract and align local regions responsive to different experts. Extensive experiments on three AGPReID benchmarks including AG-ReID.v2, CARGO and LAGPeR demonstrate that ViSA consistently achieves superior performance, with a notable 10.06\% mAP improvement on the challenging CARGO cross-view protocol. The code is available at \href{https://github.com/Cat-Zero/ViSA}{https://github.com/Cat-Zero/ViSA}.
format Preprint
id arxiv_https___arxiv_org_abs_2605_18192
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle View-Aware Semantic Alignment for Aerial-Ground Person Re-Identification
Zhang, Quan
Cai, Zeqiang
Zhao, Peiming
Wu, Jingze
Wu, Cailun
Chen, Hongbo
Lai, Jianhuang
Computer Vision and Pattern Recognition
Aerial-Ground Person Re-Identification (AGPReID) remains highly challenging due to drastic viewpoint variations between drones and fixed cameras. Existing methods typically follow a view-invariant paradigm, aligning shared features across views to achieve robustness. However, view-invariant inherently enforces part-level alignment, which ignores view-specific cues and discriminative identity information. To this end, this work proposes ViSA (View-aware Semantic Alignment), a view-aware framework that achieves cross-view semantic consistency containing an Expert-driven Token Generation Module (ETGM) and a Dual-branch Local Fusion Module (DLFM). Technically, the former constructs a set of view-aware experts to generate adaptive semantic queries that perceive viewpoint-specific patterns, while the latter leverages graph reasoning to extract and align local regions responsive to different experts. Extensive experiments on three AGPReID benchmarks including AG-ReID.v2, CARGO and LAGPeR demonstrate that ViSA consistently achieves superior performance, with a notable 10.06\% mAP improvement on the challenging CARGO cross-view protocol. The code is available at \href{https://github.com/Cat-Zero/ViSA}{https://github.com/Cat-Zero/ViSA}.
title View-Aware Semantic Alignment for Aerial-Ground Person Re-Identification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.18192