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

作者：Liu Chunxiao^*; Wang Guijin; Lin Xinggang

来源：IEICE Transactions on Information and Systems, 2013, E96D(12): 2900-2903.

DOI：10.1587/transinf.E96.D.2900

• person re-identification
• pairwise
• multiple-shot
• multiple instance learning

Learning an appearance model for person re-identification from multiple images is challenging dire 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.

• 出版日期2013-12
• 单位清华大学