面向空地行人重识别的视角感知语义对齐
View-Aware Semantic Alignment for Aerial-Ground Person Re-Identification
用一组视角感知专家生成自适应语义查询，再以图推理对齐局部区域，替代传统视角不变特征对齐；做跨视角检索或需要处理大视角差异的局部特征对齐时可直接借鉴这套专家+图推理的框架。
原文依据 constructs a set of view-aware experts to generate adaptive semantic queries that perceive viewpoint-specific patterns
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论空地行人重识别（AGPReID）由于无人机与固定相机之间存在剧烈的视角变化，仍然极具挑战性。现有方法通常遵循视角不变范式，通过在不同视角之间对齐共享特征来获得鲁棒性。然而，视角不变范式本质上强制进行部件级对齐，从而忽略了视角特有的线索与具有判别力的身份信息。为此，本文提出 ViSA（视角感知语义对齐），这是一个实现跨视角语义一致性的视角感知框架，包含专家驱动的词元生成模块（ETGM）与双分支局部融合模块（DLFM）。在技术上，前者构建一组视角感知专家，用以生成能够感知视角特有模式的自适应语义查询；后者则利用图推理，在不同视角下提取并对齐由不同专家所响应的局部区域。在 AG-ReID.v2、CARGO 与 LAGPeR 三个大规模 AGPReID 基准上的大量实验表明，ViSA 持续取得更优性能，在具有挑战性的 CARGO 跨视角协议上平均精度均值提升达 10.06%。代码将公开。
英文原文摘要 1210 字符
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 under varying viewpoints. Extensive experiments on three large-scale 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 will be available.