开放式行人再识别研究进展综述

Daoxun Xia, Fang Guo, Haojie Liu, Yong Xia

科研成果: 期刊稿件文献综述同行评审

4 引用 (Scopus)

摘要

Open-world person re-identification (Re-ID) is a task that the query person may not occur in the gallery set in an agnostic space environment. Compared with the closed-world person Re-ID, open-world Re-ID is seen as a subproblem of image retrieval, and is a more challenging and practical application research. We firstly compare and analyze the different pedestrian datasets and describe the development of existing open-set Re-ID works, the discrepancies between closed- and open-world Re-ID, and the modeling process of open-world Re-ID. Then, we focus on summarizing the research methods of open-world Re-ID, which are data-driven research methods, efficiency-driven research methods and application-driven research methods. Finally, the issues of the research and future directions for open-world Re-ID are discussed.

投稿的翻译标题Review on Research Progress of Open-World Person Re-identification
源语言繁体中文
页(从-至)449-467
页数19
期刊Shuju Caiji Yu Chuli/Journal of Data Acquisition and Processing
36
3
DOI
出版状态已出版 - 5月 2021

关键词

  • Deep learning
  • Metric learning
  • Object detection
  • Open-world person re-identification

指纹

探究 '开放式行人再识别研究进展综述' 的科研主题。它们共同构成独一无二的指纹。

引用此