Learning to Prompt Knowledge Transfer for Open-World Continual Learning

no code implementations • 22 Dec 2023 • Yujie Li, Xin Yang, Hao Wang, Xiangkun Wang, Tianrui Li

This paper studies the problem of continual learning in an open-world scenario, referred to as Open-world Continual Learning (OwCL).

Continual Learning Transfer Learning

Deep learning-based person re-identification methods: A survey and outlook of recent works

no code implementations • 10 Oct 2021 • Zhangqiang Ming, Min Zhu, Xiangkun Wang, Jiamin Zhu, Junlong Cheng, Chengrui Gao, Yong Yang, XiaoYong Wei

In recent years, with the increasing demand for public safety and the rapid development of intelligent surveillance networks, person re-identification (Re-ID) has become one of the hot research topics in the computer vision field.

Metric Learning Person Re-Identification +1

Global-Local Dynamic Feature Alignment Network for Person Re-Identification

no code implementations • 13 Sep 2021 • Zhangqiang Ming, Yong Yang, XiaoYong Wei, Jianrong Yan, Xiangkun Wang, Fengjie Wang, Min Zhu

To solve these problems, we propose a simple and efficient Local Sliding Alignment (LSA) strategy to dynamically align the local features of two images by setting a sliding window on the local stripes of the pedestrian.

Pedestrian Detection Person Re-Identification