Projects per year
Abstract
We focus on the person re-identification (re-id) problem of matching people across non-overlapping camera views. While most existing works rely on the abundance of labeled exemplars, we consider a more difficult unsupervised scenario, where no labeled exemplar is provided. One solution for unsupervised re-id that attracts much attention in the recent researches is cross-dataset transfer learning. It utilizes knowledge from multiple source datasets from different domains to enhance the unsupervised learning performance on the target domain. In previous works, much effect is taken on extraction of the generic and robust common appearances representations across domains. However, we observe that there also particular appearances in different domains. Simply ignoring these domain-unique appearances will misleading the matching schema in re-id application. Few unsupervised cross-dataset algorithms are proposed to learn the common appearances across multiple domains, even less of them consider the domain-unique representations. In this paper, we propose a novel domain-aware representation learning algorithm for unsupervised cross-dataset person re-id problem. The proposed algorithm not only learns a common appearances across-datasets but also captures the domain-unique appearances on the target dataset via minimization of the overlapped signal supports across different domains. Extensive experimental studies on benchmark datasets show superior performances of our algorithm over state-of-the-art algorithms. Sample analysis on selected samples also verifies the ability of diversity learning of our algorithm.
Original language | English |
---|---|
Title of host publication | Advanced Data Mining and Applications |
Subtitle of host publication | 15th International Conference, ADMA 2019 Dalian, China, November 21–23, 2019 Proceedings |
Editors | Jianxin Li, Sen Wang, Shaowen Qin, Xue Li, Shuliang Wang |
Place of Publication | Cham Switzerland |
Publisher | Springer |
Pages | 406-420 |
Number of pages | 15 |
ISBN (Electronic) | 9783030352318 |
ISBN (Print) | 9783030352301 |
DOIs | |
Publication status | Published - 2019 |
Event | International Conference on Advanced Data Mining and Applications 2019 - Dalian, China Duration: 21 Nov 2019 → 23 Nov 2019 Conference number: 15th http://adma2019.neusoft.edu.cn/ https://link.springer.com/book/10.1007/978-3-030-35231-8 (Proceedings) |
Publication series
Name | Lecture Notes in Computer Science |
---|---|
Publisher | Springer |
Volume | 11888 |
ISSN (Print) | 0302-9743 |
ISSN (Electronic) | 1611-3349 |
Conference
Conference | International Conference on Advanced Data Mining and Applications 2019 |
---|---|
Abbreviated title | ADMA 2019 |
Country/Territory | China |
City | Dalian |
Period | 21/11/19 → 23/11/19 |
Internet address |
Keywords
- Cross-dataset Re-ID
- Domain-aware
- Unsupervised person re-identification
Projects
- 1 Curtailed
-
Towards Data-Efficient Future Action Prediction in the Wild
Chang, X.
1/05/19 → 28/07/21
Project: Research