Title: Dependence-Aware Feature Coding for Person Re-Identification
Authors: Wang, XB; Lei, Z; Liao, SC; Guo, XJ; Yang, Y; Li, SZ
Author Full Names: Wang, Xiaobo; Lei, Zhen; Liao, Shengcai; Guo, Xiaojie; Yang, Yang; Li, Stan Z.
Source: IEEE SIGNAL PROCESSING LETTERS, 25 (4):506-510; 10.1109/LSP.2018.2803776 APR 2018
Abstract: In this letter, we focus on how to boost the performance of person re-identification by exploring the discriminative information among person pairs. A novel dependence-aware feature coding framework is proposed for this task. Specifically, we employ theHilbert-Schmidt independence criterion as the discriminative term, which is to explore the dependence between different kinds of person pairs, i.e., the same person pairs should be dependence maximized, while the different ones should be dependence minimized. Theoretical discussion and analysis on the convexity of the proposed constraint, as well as the convergence of our algorithm, are provided. Experimental results on two benchmark datasets have demonstrated the advantages of our method over the state-of-the-art alternatives.
IDS Number: FY9PF
Unique ID: WOS:000427198000003