.png){kind=icon}
返回
Modality-Specific Prototypes for Disentangled Reconstruction in modality-missing object re-identification
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2026.114641.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
基于原型的解耦重建用于模态缺失的物体重识别。
适应原型解耦与正交性和熵引导更新。
分层原型注入用于可控的两阶段模态重建。
在完整和缺失设置下，四个多模态重识别基准上取得优异结果。
Keyword:
Object re-identification
Multi-modal learning
Prototype learning
Modality-missing challenge
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Learning multi-granularity representation with transformer for visible-infrared person re-identification使用Transformer学习多粒度表示用于可见光-红外行人重识别.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏分享收藏Multi-modal person re-identification based on transformer relational regularizationINFORMATION FUSION
INFORMATION FUSIONIF15.5
PREAI
分享收藏Prototype-based sample-weighted distillation unified framework adapted to missing modality sentiment analysis适用于缺失模态情感分析的基于原型的样本加权蒸馏统一框架NEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏ICPL-ReID: Identity-Conditional Prompt Learning for Multi-Spectral Object Re-IdentificationICPL-ReID：基于身份条件提示学习的多光谱目标重识别
PREAI
分享收藏分享收藏Feature fusion and latent feature learning guided brain tumor segmentation and missing modality recovery networkPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Escaping Modal Interactions: An Efficient DESANet for Multi-Modal Object Re-Identification规避模态交互：一种高效的DESANet用于多模态目标重识别
PREAI
分享收藏
查看更多内容