Affiliations: [a] School of Computer Science, South China Normal University, Guangdong, China | [b] School of Computer Science and Engineering, Sun Yat-Sen University, Guangdong, China
Correspondence:
[*]
Corresponding authors: Hanjiang Lai and Yong Tang, School of Computer Science and Engineering, Sun Yat-Sen University, Guangdong, China. E-mail: laihanj3@mail.sysu.edu.cn;ytang@m.scnu.edu.cn.
Note: [1] Hanlu Chu and Haien Zeng contributed equally to this work.
Abstract: Many retrieval applications can benefit from multiple modalities, for which how to represent multimodal data is the critical component. Most deep multimodal learning methods typically involve two steps to construct the joint representations: 1) learning of multiple intermediate features, with each intermediate feature corresponding to a modality, using separate and independent deep models; 2) merging the intermediate features into a joint representation using a fusion strategy. However, in the first step, these intermediate features do not have previous knowledge of each other and cannot fully exploit the information contained in the other modalities. In this paper, we present a modal-aware operation as a generic building block to capture the non-linear dependencies among the heterogeneous intermediate features, which can learn the underlying correlation structures in other multimodal data as soon as possible. The modal-aware operation consists of a kernel network and an attention network. The kernel network is utilized to learn the non-linear relationships with other modalities. The attention network finds the informative regions of these modal-aware features that are favorable for retrieval. We verify the proposed modal-aware feature learning in the multimodal hashing task. The experiments conducted on three public benchmark datasets demonstrate significant improvements in the performance of our method relative to state-of-the-art methods.
