Multiple-Shot Person Re-Identification by Pairwise Multiple Instance Learning

Chunxiao LIU  Guijin WANG  Xinggang LIN  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E96-D   No.12   pp.2900-2903
Publication Date: 2013/12/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.E96.D.2900
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Image Recognition, Computer Vision
Keyword: 
person re-identification,  pairwise,  multiple-shot,  multiple instance learning,  

Full Text: PDF(418KB)>>
Buy this Article




Summary: 
Learning an appearance model for person re-identification from multiple images is challenging due to the corrupted images caused by occlusion or false detection. Furthermore, different persons may wear similar clothes, making appearance feature less discriminative. In this paper, we first introduce the concept of multiple instance to handle corrupted images. Then a novel pairwise comparison based multiple instance learning framework is proposed to deal with visual ambiguity, by selecting robust features through pairwise comparison. We demonstrate the effectiveness of our method on two public datasets.