Paths: Prompt-aware Spatio-temporal Transformer with Hierarchical Multi-modal Fusion for RGB-Event Video Person Re-Identification
Paths:面向RGB-Event视频行人重识别的感知提示的时空Transformer与分层多模态融合
机构 * Dalian University of Technology(大连理工大学)
专题命中 融合架构与评测 :multi-modal fusion(title,abstract);分类 cs.CV
AI总结 针对现有RE-VReID方法时空建模解耦、多模态融合不足的问题,提出含MAB、PST、HMF模块的Paths框架,在三个基准上验证了有效性。
Comments Accepted by ACM MM2026. More modifications may be performed