Cross-view semantic projection learning for person re-identification

• DOI: 10.1016/j.patcog.2017.04.022
• Publication Date: 2017-04-24T22:00:52Z
• Authors: Ju Dai; Ying Zhang; Huchuan Lu; Hongyu Wang
• Keywords: 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology

Abstract Feature transformation is of great importance to strengthen the descriptive power of feature representation for many classification and recognition tasks. In this paper, we propose a novel cross-view semantic projection learning method for extracting latent semantics from the hand-crafted features. Specifically, the shared latent basis matrix, the view-specific semantic projection functions and the optimal associations of different views are jointly learned in a unified matrix factorization framework, to get a common semantic space where images of the same person can be well characterized. We further present a generalization of the approach to multiple views. Extensive experiments on a series of challenging datasets highlight the superiorities of the proposed algorithm and demonstrate the effectiveness of the generalized version in multi-view person re-identification applications.