发表机构
School of Automation, Southeast University; Faculty of Information Engineering and Automation, Kunming University of Science and Technology; School of Computer Science and Engineering, University of New South Wales; School of Sports Training, Tianjin University of Sport; Tianjin University; National University of Defense Technology（东南大学自动化学院; 昆明理工大学信息工程与自动化学院; 新南威尔士大学计算机科学与工程学院; 天津体育学院运动训练学院; 天津大学; 国防科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对空-地跨视角参考人物检测的挑战，本文提出首个该任务基准A-PAIR及ICRG框架，将对级F1从16.65%提至22.28%，验证了配对检测与身份一致推理的必要性。
AI 中文摘要
空-地跨视角参考人物检测是集体具身智能的语言-感知-控制链中的必要组成部分，它将语言指令定位到同一物理目标，之后地面智能体和空中智能体才能协调下游动作。现有的参考表达式理解和开放词汇定位方法未同时考虑跨视角身份一致性，因此无法满足空-地跨视角参考人物检测（AGCV-RPD）的需求，该任务存在相似行人干扰项、空中外观线索薄弱、跨视角身份一致性等挑战。为研究该问题，我们推出首个综合AGCV-RPD基准Air-Ground Paired Identity-Aware Referring（A-PAIR），包含22137个跨视角参考样本。为高效构建A-PAIR，我们提出半自动化标注框架Factorized Annotation and Referential Alignment（FARA），该框架以更低成本生成分解式参考描述和身份一致性监督信号。我们提出身份一致的参考定位（ICRG）框架，它结合分解式参考定位、候选完整性监督和跨视角一致性校准，用于联合空-地对选择。ICRG在地面、空中及对级别的检测性能上优于强基线，将对级F1值从16.65%提升至22.28%。这些结果表明AGCV-RPD需要配对检测和身份一致的推理。
英文摘要
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.
