论文浏览

【论文题目】Modeling intra- and inter-pair correlation via heterogeneous high-order preserving for cross-modal retrieval

【作    者】Leiquan Wang, Weichen Sun, Zhicheng Zhao, Fei Su        点击下载PDF全文

【关 键 字】Cross-modal retrieval, Heterogeneous high-order preserving, Correlation learning Kernel

【发表刊物/会议】
    Signal Processing

【摘    要】
     Cross modal (e.g., text-to-image or image-to-text) retrieval has received great attention with the flushed multi-modal social media data. It is of considerable challenge to stride across the heterogeneous gap between modalities. Existing methods project different modalities into a common space by minimizing the distance within the heterogeneous pairs (intra-pair) of the new latent space. However, the relationship among these multi-modal pairs (inter-pair) are neglected, which are beneficial to eliminate the heterogeneity. In this paper, we propose a novel algorithm based on canonical correlation analysis by considering the high-order relationship among pairs (HCCA) for cross-modal retrieval. Supervised with additional semantic labels and unsupervised without semantic labels are simultaneously considered by treating the intra- and inter-pair correlation discriminatively. Moreover, kernel tricks are also performed on HCCA to learn a non-linear projection, termed HKCCA. Extensive experiments conducted on three public datasets demonstrate the superiority of the proposed methods compared with the state-of-the-art approaches in cross modal retrieval.

【发 表 年】2017

【发 表 月】2

【类    别】计算机视觉


Tel: 086-010-62283118 邮编:100876
地址:北京市海淀区西土城路10号北京邮电大学教二楼多媒体中心
北京市海淀区西土城路十号113#信箱
版权所有:北京邮电大学多媒体通信与模式识别研究室 京ICP证14002347号