A-PAIR: A Benchmark and Identity-Consistent Grounding Framework for Air-Ground Cross-View Referring Person Detection

2026-08-28

AI Summary

本文针对空中-地面跨视角指代人物检测问题，提出A-PAIR基准及身份一致的定位框架，通过因子化标注与参照对齐方法有效构建数据集，并利用身份一致的指代定位框架提高检测性能。

Abstract

Air-ground cross-view referring person detection is a necessary component in the language-to-perception-to-control chain of collective embodied intelligence, grounding a language command into the same physical target before ground and aerial agents can coordinate downstream actions. Existing referring expression comprehension and open-vocabulary grounding methods do not jointly account for cross-view identity consistency, making them insufficient for Air-Ground Cross-View Referring Person Detection (AGCV-RPD), which involves similar pedestrian distractors, weak aerial appearance cues, and cross-view identity consistency. To study this problem, we introduce Air-Ground Paired Identity-Aware Referring (A-PAIR), the first comprehensive AGCV-RPD benchmark, containing 22,137 cross-view referring samples. To construct A-PAIR efficiently, we propose Factorized Annotation and Referential Alignment (FARA), a semi-automatic annotation framework that generates factorized referring descriptions and identity-consistency supervision at reduced cost. We propose Identity-Consistent Referring Grounding (ICRG), a framework that combines factorized referential grounding, candidate-completeness supervision, and cross-view consistency calibration for joint air-ground pair selection. ICRG improves ground, aerial, and pair-level detection over strong baselines, increasing pair F1 from 16.65% to 22.28%. These results show that AGCV-RPD requires paired detection and identity-consistent reasoning.

Problem

• Air-Ground Cross-View Referring Person Detection
• Cross-View Identity Consistency
• Pedestrian Distractors
• Aerial Appearance Cues

Innovation

• Identity-Consistent Referring Grounding
• Factorized Annotation and Referential Alignment
• Air-Ground Cross-View Referring Person Detection