Abstract
We propose \textbf{KeyRe-ID}, a keypoint-guided video-based person re-identification framework consisting of global and local branches that leverage human keypoints for enhanced spatiotemporal representation learning. The global branch captures holistic identity semantics through Transformer-based temporal aggregation, while the local branch dynamically segments body regions based on keypoints to generate fine-grained, part-aware features. Extensive experiments on MARS and iLIDS-VID benchmarks demonstrate state-of-the-art performance, achieving 91.73\% mAP and 97.32\% Rank-1 accuracy on MARS, and 96.00\% Rank-1 and 100.0\% Rank-5 accuracy on iLIDS-VID. The code for this work will be publicly available on GitHub upon publication.
Abstract (translated)
我们提出了**KeyRe-ID**，这是一种基于关键点的视频人物重识别框架，该框架由全局和局部两部分组成，并利用人体关键点进行增强的空间时间表示学习。全局分支通过基于Transformer的时间聚合捕捉整体身份语义，而局部分支则根据关键点动态分割身体区域以生成细粒度、部件感知特征。 在MARS和iLIDS-VID基准测试中进行了广泛的实验，证明了该方法的先进性能，在MARS上达到了91.73% mAP和97.32% Rank-1准确率，在iLIDS-VID上则分别实现了96.00% Rank-1和100.0% Rank-5的准确性。 此工作的代码将在发布后在GitHub上公开。
URL
https://arxiv.org/abs/2507.07393
