CVPR2019-行人重识别论文汇总

本文汇总了CVPR2019大会中关于行人重识别领域的19篇重要论文,涵盖了从域自适应、视角分析、红外可见光匹配到弱监督学习等前沿研究方向。

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

当时整理的比较简单,在知乎上发现了更全面的整理:【CVPR2019正式公布】行人重识别论文 附下载链接

根据paper list搜到19篇:

  1. Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification

  2. Dissecting Person Re-identification from the Viewpoint of Viewpoint

  3. Learning to Reduce Dual-level Discrepancy for Infrared-Visible Person Re-identification

  4. Densely Semantically Aligned Person Re-Identification

  5. Generalizable Person Re-identification by Domain-Invariant Mapping Network

  6. Re-ranking via Metric Fusion for Object Retrieval and Person Re-identification

  7. Weakly Supervised Person Re-Identification

  8. Query-guided End-to-End Person Search

  9. Distilled Person Re-identification: Towards a More Scalable System

  10. Joint Discriminative and Generative Learning for Person Re-identification(Oral)

  11. Unsupervised Person Re-identification by Soft Multilabel Learning(Oral)

  12. Learning Context Graph for Person Search(Oral)

  13. Patch Based Discriminative Feature Learning for Unsupervised Person Re-identification

  14. Attribute-Driven Feature Disentangling and Temporal Aggregation for Video Person Re-Identification

  15. AANet: Attribute Attentio Network for Person Re-Identification

  16. VRSTC: Occlusion-Free Video Person Re-Identification

  17. Adaptive Transfer Network for Cross-Domain Person Re-Identification

  18. Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training

  19. Interaction-and-Aggregation Network for Person Re-identification

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