首个高空航拍与地面视频行人重识别挑战赛，突破视角差异难题。
AG-VPReID 2025: Aerial-Ground Video-based Person Re-identification Challenge Results
- 构建多源视频数据集，融合无人机、监控和穿戴设备影像。
- 最优模型在跨视角重识别中达72.28%准确率，超越现有基准。
- 适合关注智能安防与跨视角识别的研究者与工程师。
跨航拍与地面视角的行人重识别（ReID）对大规模监控与公共安全至关重要。尽管地面场景已有显著进展，但因视角差异大、尺度变化及遮挡问题，实现跨域匹配仍具挑战。本文基于AG-ReID 2023成果，推出首个面向高海拔（80–120米）航拍-地面视频的大型视频级重识别挑战赛——AG-VPReID 2025。该挑战基于新构建的AG-VPReID数据集，包含3,027个身份、超过13,500条轨迹及约370万帧画面，数据源自无人机、闭路电视和可穿戴摄像头。共4支国际团队参与，提出从多流架构到基于Transformer的时间建模，以及物理启发式建模等方法。领先方案X-TFCLIP（UAM）在航拍→地面设置中取得72.28% Rank-1准确率，在地面→航拍设置中达70.77%，显著超越现有基线，凸显数据集复杂性。更多信息请访问官方页面：https://agvpreid25.github.io。
原文摘要 · Abstract (English)
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 https://agvpreid25.github.io.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。