用人体关键点指导视频行人重识别，提升定位与身份匹配精度
KeyRe-ID: Keypoint-Guided Person Re-Identification using Part-Aware Representation in Videos
- 通过关键点动态分割身体区域，生成局部精细特征
- 在MARS上达91.73% mAP，iLIDS-VID上达100.0% Rank-5
- 适合需要高精度视频行人识别的安防与监控场景
我们提出KeyRe-ID，一种基于关键点引导的视频行人重识别框架，包含全局与局部双分支。全局分支采用Transformer进行时序聚合，捕捉整体身份语义；局部分支根据关键点动态分割身体区域，生成细粒度的部件感知特征。在MARS和iLIDS-VID数据集上的大量实验表明，该方法达到领先性能：在MARS上取得91.73% mAP和97.32% Rank-1准确率，在iLIDS-VID上实现96.00% Rank-1和100.0% Rank-5准确率。代码将在论文发表后公开于GitHub。
原文摘要 · Abstract (English)
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.
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。