返回
Multi-granularity collaborative constraint feature alignment network for unsupervised person re-identification
DOI:10.1016/j.patcog.2026.113676.png)
摘要
En 中文
• 提出层次化多粒度架构用于无监督ReID学习。 • 引入约束损失以显式对齐多尺度特征。 • 设计CCF模块在内存库初始化前过滤和对齐粒度特征。 • 在四个数据集上验证有效性与跨数据集适应性。
Keyword:
unsupervised person re-identification
multi-granularity architecture
constraint losses
feature alignment
cross-dataset adaptability
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
PATTERN RECOGNITION
IF7.6
Beyond Part Models: Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline)
Discriminative Identity-Feature Exploring and Differential Aware Learning for Unsupervised Person Re-Identification用于无监督人员重新识别的区分性身份特征探索和差异意识学习

