Journal
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
Volume 42, Issue 2, Pages 371-385Publisher
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2019.2928294
Keywords
Feature extraction; Cameras; Task analysis; Computer architecture; Computational modeling; Adaptation models; Clothing; Person re-identification; multi-scale deep learning; self-attention; domain generalization
Funding
- NSFC [61702108, 61622204, 61572138]
- STCSM Project [16JC1420400]
- Shanghai Municipal Science and Technology Major Projects [2017SHZDZX01, 2018SHZDZX01]
- ZJLab
Ask authors/readers for more resources
Person re-identification (re-id) aims to match people across non-overlapping camera views in a public space. This is a challenging problem because the people captured in surveillance videos often wear similar clothing. Consequently, the differences in their appearance are typically subtle and only detectable at particular locations and scales. In this paper, we propose a deep re-id network (MuDeep) that is composed of two novel types of layers - a multi-scale deep learning layer, and a leader-based attention learning layer. Specifically, the former learns deep discriminative feature representations at different scales, while the latter utilizes the information from multiple scales to lead and determine the optimal weightings for each scale. The importance of different spatial locations for extracting discriminative features is learned explicitly via our leader-based attention learning layer. Extensive experiments are carried out to demonstrate that the proposed MuDeep outperforms the state-of-the-art on a number of benchmarks and has a better generalization ability under a domain generalization setting.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available