Co-Metric Learning for Person Re-Identification
Author
Source
Issue
Vol. 2018, Issue 2018 (31 Dec. 2018), pp.1-9, 9 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2018-07-15
Country of Publication
Egypt
No. of Pages
9
Main Subjects
Information Technology and Computer Science
Abstract EN
Person re-identification, aiming to identify the same pedestrian images across disjoint camera views, is a key technique of intelligent video surveillance.
Although existing methods have developed both theories and experimental results, most of effective ones pertain to fully supervised training styles, which suffer the small sample size (SSS) problem a lot, especially in label-insufficient practical applications.
To bridge SSS problem and learning model with small labels, a novel semisupervised co-metric learning framework is proposed to learn a discriminative Mahalanobis-like distance matrix for label-insufficient person re-identification.
Different from typical co-training task that contains multiview data originally, single-view person images are firstly decomposed into pseudo two views, and then metric learning models are produced and jointly updated based on both pseudo-labels and references iteratively.
Experiments carried out on three representative person re-identification datasets show that the proposed method performs better than state of the art and possesses low label sensitivity.
American Psychological Association (APA)
Leng, Qingming. 2018. Co-Metric Learning for Person Re-Identification. Advances in Multimedia،Vol. 2018, no. 2018, pp.1-9.
https://search.emarefa.net/detail/BIM-1118422
Modern Language Association (MLA)
Leng, Qingming. Co-Metric Learning for Person Re-Identification. Advances in Multimedia No. 2018 (2018), pp.1-9.
https://search.emarefa.net/detail/BIM-1118422
American Medical Association (AMA)
Leng, Qingming. Co-Metric Learning for Person Re-Identification. Advances in Multimedia. 2018. Vol. 2018, no. 2018, pp.1-9.
https://search.emarefa.net/detail/BIM-1118422
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1118422