Learning Invariance From Generated Variance for Unsupervised Person Re-Identification

Author:

Chen Hao1ORCID,Wang Yaohui1,Lagadec Benoit2,Dantcheva Antitza1ORCID,Bremond Francois1ORCID

Affiliation:

1. Inria and Université Côte d'Azur, Valbonne, France

2. European Systems Integration, Le Cannet, France

Funder

National Research Agency

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Applied Mathematics,Artificial Intelligence,Computational Theory and Mathematics,Computer Vision and Pattern Recognition,Software

Reference77 articles.

1. Generative adversarial nets;goodfellow;Proc Int Conf Neural Inf Process,2014

2. A Bottom-Up Clustering Approach to Unsupervised Person Re-Identification

3. Random Erasing Data Augmentation

4. Learning to adapt invariance in memory for person re-identification;zhong;IEEE Trans Pattern Anal Mach Intell,2021

5. Domain adaptation through synthesis for unsupervised person re-identification;bak;Proc Eur Conf Comput Vis,2018

Cited by 9 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Viewpoint Disentangling and Generation for Unsupervised Object Re-ID;ACM Transactions on Multimedia Computing, Communications, and Applications;2024-01-22

2. Asymmetric double networks mutual teaching for unsupervised person Re-identification;Neural Networks;2024-01

3. Unsupervised Person Re-identification via Differentiated Color Perception Learning;Communications in Computer and Information Science;2024

4. IQAGA: Image Quality Assessment-Driven Learning with GAN-Based Dataset Augmentation for Cross-Domain Person Re-Identification;Proceedings of the 12th International Symposium on Information and Communication Technology;2023-12-07

5. Bridge the gap between supervised and unsupervised learning for fine-grained classification;Information Sciences;2023-11

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3