DMPT: Decoupled Modality-Aware Prompt Tuning for Multi-Modal Object Re-Identification

Minghui Lin, Shu Wang,Xiang Wang, Jianhua Tang, Longbin Fu,Zhengrong Zuo,Nong Sang

IEEE/CVF Winter Conference on Applications of Computer Vision（2025）

引用 0|浏览0

关键词

Multimodal Objective,Semantic Information,Vision Transformer,Multimodal Input,Text Encoder,Extract Semantic Information,Direct Interaction,Basic Characteristics,Visual Features,ImageNet,Benchmark Datasets,Latent Space,Textual Descriptions,Shared Space,Linear Layer,Mutual Coupling,Feature Alignment,Multimodal Features,Triplet Loss,Internal Interactions,External Interactions,Cross-modal Interactions,Foundation Model,Re-identification Task,Identity Recognition,Multimodal Tasks

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要