CLIP4VI-ReID: Learning Modality-shared Representations via CLIP Semantic Bridge for Visible-Infrared Person Re-identification
CLIP4VI-ReID:通过CLIP语义桥学习模态共享表征用于可见光-红外行人重识别
机构 * Shandong Key Laboratory of Ubiquitous Intelligent Computing, School of Information Science and Engineering, University of Jinan(山东 ubiquitous 智能计算重点实验室,信息科学与工程学院,济南大学) ; College of Information Science and Technology & College of Artificial Intelligence, Nanjing Forestry University(信息科学与技术学院及人工智能学院,南京林业大学) ; Computer Systems Engineering Department, Universidad Politécnica de Madrid(计算机系统工程系,马德里理工大学)
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CLIP4VI-ReID网络,通过TSG、IFE、HSA模块及CLIP语义桥实现跨模态对齐,在VI-ReID任务上取得优于现有方法的性能。
Comments This article has been accepted for publication in IEEE Transactions on Biometrics, Behavior, and Identity Science