Abstract
Person re-identification (ReID) across aerial and ground vantage points has become crucial for large-scale surveillance and public safety applications. Although significant progress has been made in ground-only scenarios, bridging the aerial-ground domain gap remains a formidable challenge due to extreme viewpoint differences, scale variations, and occlusions. Building upon the achievements of the AG-ReID 2023 Challenge, this paper introduces the AG-VPReID 2025 Challenge - the first large-scale video-based competition focused on high-altitude (80-120m) aerial-ground ReID. Constructed on the new AG-VPReID dataset with 3,027 identities, over 13,500 tracklets, and approximately 3.7 million frames captured from UAVs, CCTV, and wearable cameras, the challenge featured four international teams. These teams developed solutions ranging from multi-stream architectures to transformer-based temporal reasoning and physics-informed modeling. The leading approach, X-TFCLIP from UAM, attained 72.28% Rank-1 accuracy in the aerial-to-ground ReID setting and 70.77% in the ground-to-aerial ReID setting, surpassing existing baselines while highlighting the dataset's complexity. For additional details, please refer to the official website at this https URL.
Abstract (translated)
人员再识别（ReID）在空中和地面视角之间的跨域应用对于大规模监控和公共安全至关重要。尽管仅限于地面场景的进展显著，但由于极端视点差异、尺度变化以及遮挡问题，跨越空地领域的挑战依然巨大。基于AG-ReID 2023挑战赛的成绩，本文介绍了AG-VPReID 2025挑战赛——首个专注于高空（80至120米）空中与地面再识别的大规模视频竞赛。该挑战赛建立在新发布的AG-VPReID数据集之上，该数据集包含3,027个身份、超过13,500条轨迹片段以及约370万帧图像，这些图像由无人机、CCTV和可穿戴相机采集而成。四支国际团队参与了此次挑战赛，并开发了一系列解决方案，包括多流架构到基于Transformer的时间推理及物理信息建模技术。 领先的方法是UAM提出的X-TFCLIP，在空中转地面再识别任务中实现了72.28%的Rank-1准确率，在地面向空中再识别任务中则达到了70.77%，这一成绩超越了现有基线，同时展示了数据集的独特复杂性。欲了解更多信息，请参阅官方网址：[this https URL]（请将方括号中的内容替换为实际链接）。
URL
https://arxiv.org/abs/2506.22843
