有时间再看的文章

博客汇总了多篇行人重识别相关的研究论文,涉及用哈希做重识别、选择性卷积描述符聚合用于细粒度图像检索等内容,还提及平均池化、利用embedding生成纹理图像等技术,标签为深度学习。

摘要生成于 C知道 ,由 DeepSeek-R1 满血版支持, 前往体验 >

Deep Multi-Index Hashing for Person Re-Identification 

https://arxiv.org/pdf/1905.10980.pdf

用哈希来做重识别

 

Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval

https://arxiv.org/pdf/1604.04994.pdf

平均池化

 

Semantics-Aligned Representation Learning for Person Re-identification

https://arxiv.org/pdf/1905.13143.pdf

利用embedding生成纹理图像,UV空间

 

Unified Multifaceted Feature Learning for Person Re-Identification

https://arxiv.org/pdf/1911.08651.pdf

erase

 

MagnifierNet: Towards Semantic Adversary and Fusion for Person Re-identification

https://arxiv.org/pdf/2002.10979.pdf

align

 

Hierarchical and Efficient Learning for Person Re-Identification

https://arxiv.org/pdf/2005.08812.pdf

Random Polygon Erasing,多种东西组合

 

Self-Critical Attention Learning for Person Re-Identification

https://openaccess.thecvf.com/content_ICCV_2019/papers/Chen_Self-Critical_Attention_Learning_for_Person_Re-Identification_ICCV_2019_paper.pdf

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值