NEXT: Multi-Grained Mixture of Experts via Text-Modulation for Multi-Modal Object Re-Identification
NEXT: 通过文本调制的多粒度专家混合实现多模态物体重识别
机构 * State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology(光电信息采集与防护技术国家重点实验室) ; Anhui Provincial Key Laboratory of Multimodal Cognitive Computation(安徽省多模态认知计算重点实验室) ; School of Artificial Intelligence(人工智能学院) ; Anhui University(安徽大学) ; State Key Laboratory of Multimodal Artificial Intelligence Systems(多模态人工智能系统国家重点实验室) ; New Laboratory of Pattern Recognition(模式识别新实验室) ; CASIA(中国科学院自动化所) ; University of Chinese Academy of Sciences(中国科学院大学) ; School of Computing and Mathematical Sciences(计算与数学科学学院) ; University of Greenwich(格林威治大学)
AI总结 本文提出NEXT框架,通过文本调制分离语义和结构分支,融合多粒度专家特征,提升多模态物体重识别性能。