Abstract
Extreme far-distance video person re-identification (ReID) is particularly challenging due to scale compression, resolution degradation, motion blur, and aerial-ground viewpoint mismatch. As camera altitude and subject distance increase, models trained on close-range imagery degrade significantly. In this work, we investigate how large-scale vision-language models can be adapted to operate reliably under these conditions. Starting from a CLIP-based baseline, we upgrade the visual backbone from ViT-B/16 to ViT-L/14 and introduce backbone-aware selective fine-tuning to stabilize adaptation of the larger transformer. To address noisy and low-resolution tracklets, we incorporate a lightweight temporal attention pooling mechanism that suppresses degraded frames and emphasizes informative observations. We retain adapter-based and prompt-conditioned cross-view learning to mitigate aerial-ground domain shifts, and further refine retrieval using improved optimization and k-reciprocal re-ranking. Experiments on the DetReIDX stress-test benchmark show that our approach achieves mAP scores of 46.69 (A2G), 41.23 (G2A), and 22.98 (A2A), corresponding to an overall mAP of 35.73. These results show that large-scale vision-language backbones, when combined with stability-focused adaptation, significantly enhance robustness in extreme far-distance video person ReID.
Abstract (translated)
极端远距离视频行人重识别（ReID）由于尺度压缩、分辨率退化、运动模糊以及空中-地面视角不匹配而极具挑战性。随着摄像机高度和主体距离的增加，在近距图像上训练的模型性能会显著下降。本研究探索了如何调整大规模视觉-语言模型以在此类条件下可靠运行。我们从基于CLIP的基线出发，将视觉主干网络从ViT-B/16升级至ViT-L/14，并引入主干网络感知的选择性微调以稳定大型Transformer的适应过程。为应对噪声和低分辨率的轨迹段，我们融入了轻量级时序注意力池化机制，以抑制退化帧并突显信息丰富的观测。我们保留了基于适配器和提示条件化的跨视角学习策略以缓解空中-地面域偏移，并进一步通过改进的优化与k-倒数重排序技术精炼检索结果。在DetReIDX压力测试基准上的实验表明，我们的方法在A2G、G2A和A2A场景下分别达到46.69、41.23和22.98的mAP分数，整体mAP为35.73。这些结果证明，结合稳定性导向的适配策略，大规模视觉-语言主干网络能显著提升极端远距离视频行人ReID的鲁棒性。
URL
https://arxiv.org/abs/2604.04183
