Cross-domain latent space projection for person re-identification

Nan Pu; Song Wu D.D.S.; Li Qian M.D.; Guoqiang Xiao D.D.S.

doi:10.1117/12.2303477

10 April 2018 Cross-domain latent space projection for person re-identification

Nan Pu, Song Wu D.D.S., Li Qian M.D., Guoqiang Xiao D.D.S.

Proceedings Volume 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017); 106153W (2018) https://doi.org/10.1117/12.2303477
Event: Ninth International Conference on Graphic and Image Processing, 2017, Qingdao, China

Abstract

In this paper, we research the problem of person re-identification and propose a cross-domain latent space projection (CDLSP) method to address the problems of the absence or insufficient labeled data in the target domain. Under the assumption that the visual features in the source domain and target domain share the similar geometric structure, we transform the visual features from source domain and target domain to a common latent space by optimizing the object function defined in the manifold alignment method. Moreover, the proposed object function takes into account the specific knowledge in the re-id with the aim to improve the performance of re-id under complex situations. Extensive experiments conducted on four benchmark datasets show the proposed CDLSP outperforms or is competitive with stateof- the-art methods for person re-identification.

Citation Download Citation

Nan Pu, Song Wu D.D.S., Li Qian M.D., and Guoqiang Xiao D.D.S. "Cross-domain latent space projection for person re-identification", Proc. SPIE 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017), 106153W (10 April 2018); https://doi.org/10.1117/12.2303477

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available