Research Area:  Machine Learning

Abstract:

Multimodal representation learning, which aims to narrow the heterogeneity gap among different modalities, plays an indispensable role in the utilization of ubiquitous multimodal data. Due to the powerful representation ability with multiple levels of abstraction, deep learning-based multimodal representation learning has attracted much attention in recent years. In this paper, we provided a comprehensive survey on deep multimodal representation learning which has never been concentrated entirely. To facilitate the discussion on how the heterogeneity gap is narrowed, according to the underlying structures in which different modalities are integrated, we category deep multimodal representation learning methods into three frameworks: joint representation, coordinated representation, and encoder-decoder. Additionally, we review some typical models in this area ranging from conventional models to newly developed technologies. This paper highlights on the key issues of newly developed technologies, such as encoder-decoder model, generative adversarial networks, and attention mechanism in a multimodal representation learning perspective, which, to the best of our knowledge, have never been reviewed previously, even though they have become the major focuses of much contemporary research. For each framework or model, we discuss its basic structure, learning objective, application scenes, key issues, advantages, and disadvantages, such that both novel and experienced researchers can benefit from this survey. Finally, we suggest some important directions for future work.

Keywords:  
Multimodal representation learning
Multimodal deep learning
Deep multimodal fusion
Multimodal translation
Multimodal adversarial learning

Author(s) Name:   Wenzhong Guo; Jianwen Wang; Shiping Wang

Publisher name:  IEEE

DOI:  10.1109/ACCESS.2019.2916887

Volume Information:  Volume: 7, Page(s): 63373 - 63394

Paper Link:   https://ieeexplore.ieee.org/document/8715409