Xu Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Xu Wang has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Guowen Kuang
Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area, Shenzhen Polytechnic University, Shenzhen 518055, China
1 shared publication - Haojun Zhang
Yangzhou University
1 shared publication Junzhi Yu
1 shared publication- Tingting Li
Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area, Shenzhen Polytechnic, China and School of Electronics and Information Engineering, University of Science and Technology Liaoning, China
1 shared publication - Yaqiao Liao
Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area, Shenzhen Polytechnic, China and School of Electronics and Information Engineering, University of Science and Technology Liaoning, China
1 shared publication - Yuequan Yang
Yangzhou University
1 shared publication
Latest Publications
- Open Access
- 23 December 2022
- Published by Association for Computing Machinery (ACM)
- p. 149-156
Information Bottleneck Enhanced Video-based Person Re-identification
Person re-identification has great potential in applications of public security. However, non-discriminative information like background noise still hinders further improvement of current person re-identification algorithms. This paper proposes an information bottleneck-enhanced video-based person re-identification algorithm concentrating on discriminative information. Specifically, the spatial-temporal information purification (STIP) module is designed to filter out irrelevant information and the variance of information is estimated to weigh the importance of each feature dimension. Our method is evaluated on MARS and results show that it pays more attention to discriminative information and suppresses the irrelevant feature.
- 23 December 2022
- Published by Association for Computing Machinery (ACM)
- p. 149-156
Open AccessInformation Bottleneck Enhanced Video-based Person Re-identification
Person re-identification has great potential in applications of public security. However, non-discriminative information like background noise still hinders further improvement of current person re-identification algorithms. This paper proposes an information bottleneck-enhanced video-based person re-identification algorithm concentrating on discriminative information. Specifically, the spatial-temporal information purification (STIP) module is designed to filter out irrelevant information and the variance of information is estimated to weigh the importance of each feature dimension. Our method is evaluated on MARS and results show that it pays more attention to discriminative information and suppresses the irrelevant feature.