Temporal Prototyping and Hierarchical Alignment for Unsupervised Video-based Visible-Infrared Person Re-Identification
时序原型与层次对齐用于无监督的基于视频的可见-红外人员重识别
机构 * College of Control Science and Engineering, Zhejiang University(控制科学与工程学院,浙江大学) ; School of Computer Science and Technology, Zhejiang University of Water Resources and Electric Power(计算机科学与技术学院,浙江水利电力大学)
专题命中 红外-可见光融合 :visible-infrared(title,abstract);分类 cs.CV
AI总结 本文提出HiTPro框架,通过时序感知特征编码器和层次交叉原型对齐,解决无监督视频基于可见-红外人员重识别问题,实现跨模态一致性与不变性。