Zirui Zhang

Zirui Zhang

Auto-generated profile, based on publicly available information

Zirui Zhang

School of ElectronicInformation and Electrical Engineering, Shanghai Jiao Tong University, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 December 2023 in ACM Transactions on Multimedia Computing, Communications, and Applications
Verified
Journal Article
Open access
Suncheng XiangSuncheng Xiang
Suncheng Xiang
Dahong QianDahong Qian
Dahong Qian
JGJingsheng Gao
Jingsheng Gao
ZZZirui Zhang
Zirui Zhang
TLTing Liu
Ting Liu
YFYuzhuo Fu
Yuzhuo Fu
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 .