Zirui Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Zirui Zhang has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Dahong Qian
Shanghai Jiao Tong University
1 shared publication - Jingsheng Gao
Shanghai Jiao Tong University, Shanghai, China
1 shared publication - Suncheng Xiang
Shanghai Jiao Tong University
1 shared publication - Ting Liu
Shanghai Jiao Tong University, Shanghai, China
1 shared publication - Yuzhuo Fu
Shanghai Jiao Tong University
1 shared publication
Latest Publications
- Open Access
- 9 December 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (3) , 1-17
Rethinking Person Re-Identification via Semantic-based Pretraining
Pretraining is a dominant paradigm in computer vision. Generally, supervised ImageNet pretraining is commonly used to initialize the backbones of person re-identification (Re-ID) models. However, recent works show a surprising result that CNN-based pretraining on ImageNet has limited impacts on Re-ID system due to the large domain gap between ImageNet and person Re-ID data. To seek an alternative to traditional pretraining, here we investigate semantic-based pretraining as another method to utilize additional textual data against ImageNet pretraining. Specifically, we manually construct a diversified FineGPR-C caption dataset for the first time on person Re-ID events. Based on it, a pure semantic-based pretraining approach named VTBR is proposed to adopt dense captions to learn visual representations with fewer images. We train convolutional neural networks from scratch on the captions of FineGPR-C dataset, and then transfer them to downstream Re-ID tasks. Comprehensive experiments conducted on benchmark datasets show that our VTBR can achieve competitive performance compared with ImageNet pretraining—despite using up to 1.4× fewer images, revealing its potential in Re-ID pretraining. Our source code is also publicly available at https://github.com/JeremyXSC/VTBR .
- 9 December 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (3) , 1-17
Open AccessRethinking Person Re-Identification via Semantic-based Pretraining
Pretraining is a dominant paradigm in computer vision. Generally, supervised ImageNet pretraining is commonly used to initialize the backbones of person re-identification (Re-ID) models. However, recent works show a surprising result that CNN-based pretraining on ImageNet has limited impacts on Re-ID system due to the large domain gap between ImageNet and person Re-ID data. To seek an alternative to traditional pretraining, here we investigate semantic-based pretraining as another method to utilize additional textual data against ImageNet pretraining. Specifically, we manually construct a diversified FineGPR-C caption dataset for the first time on person Re-ID events. Based on it, a pure semantic-based pretraining approach named VTBR is proposed to adopt dense captions to learn visual representations with fewer images. We train convolutional neural networks from scratch on the captions of FineGPR-C dataset, and then transfer them to downstream Re-ID tasks. Comprehensive experiments conducted on benchmark datasets show that our VTBR can achieve competitive performance compared with ImageNet pretraining—despite using up to 1.4× fewer images, revealing its potential in Re-ID pretraining. Our source code is also publicly available at https://github.com/JeremyXSC/VTBR .