Selected Publications

Click title to project page

In CVPR (oral), 2019
PDF Code Supp
Lacking pairwise labels is the fundamental challenge in unsupervised person re-identification. We propose a novel paradigm to learn soft labels that are interpretable and lead to superior performances. Tackling this fundamental issue allows future research to ultimately approach supervised performances.

In ICCV, 2017
PDF Code
Most existing person re-identification methods require substantial labeled data, yet this severely limits the scalability to real-world applications. We demonstrate the potential of unsupervised person re-identification by introducing a key principle: camera view-aware modeling. For the first time, we show that an unsupervised method can yield strong performances even compared to supervised methods. After we publish this work, unsupervised person re-identification has received increasing research attentions.

Recent Publications

Click title to project page

. Unsupervised Person Re-identification by Soft Multilabel Learning. In CVPR (oral), 2019.

PDF Code Supp

. Patch Based Discriminative Feature Learning for Unsupervised Person Re-identification. In CVPR, 2019.

PDF Code

. Unsupervised Person Re-identification by Deep Asymmetric Metric Embedding. TPAMI, 2019.

PDF Code

. MIXGAN: Learning Concepts from Different Domains for Mixture Generation. In IJCAI, 2018.

PDF

. Cross-view Asymmetric Metric Learning for Unsupervised Person Re-identification. In ICCV, 2017.

PDF Code

. RGB-infrared Cross-modality Person Re-identification. In ICCV, 2017.

PDF Code

Awards

  • Chinese National Scholarship (1⁄248), by Minister of Education of China, 2019
  • Chinese National Scholarship (1⁄248), by Minister of Education of China, 2018
  • Outstanding Undergraduate Award (Top 5%), by Sun Yat-sen University, 2017
  • Outstanding Undergraduate Thesis Award (Top 5%), by Sun Yat-sen University, 2017
  • Chinese National Scholarship (2⁄105), by Minister of Education of China, 2016

Service

  • Reviewer for CVPR’18, CVPR’20
  • Aiming for better reproducibility, I maintain open-source codes for all my first-authored work. Please check my github page at https://github.com/KovenYu

Contact